[GH-ISSUE #4900] MiniCPM-Llama3-V-2_5 #3094

New Issue

GiteaMirror · 2026-04-12T13:32:00-05:00

GiteaMirror commented

2026-04-12 13:32:00 -05:00

Originally created by @kotaxyz on GitHub (Jun 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4900

This is the best open source vision model i have ever tried , We need support for it in ollama

Originally created by @kotaxyz on GitHub (Jun 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4900 This is the best open source vision model i have ever tried , We need support for it in ollama

GiteaMirror added the model label 2026-04-12 13:32:00 -05:00

GiteaMirror commented

2026-04-12 13:32:01 -05:00

@GingerNg commented on GitHub (Jun 7, 2024):

https://ollama.com/hhao/openbmb-minicpm-llama3-v-2_5 I tried to pull model, but failed many times,

@GingerNg commented on GitHub (Jun 7, 2024): https://ollama.com/hhao/openbmb-minicpm-llama3-v-2_5 I tried to pull model, but failed many times, ![image](https://github.com/ollama/ollama/assets/13898738/aa2d21c3-2251-413b-a9e4-a0e5ed53ed03)

GiteaMirror commented

2026-04-12 13:32:01 -05:00

@Greatz08 commented on GitHub (Jun 8, 2024):

@kotaxyz did you tried to download gguf format files and create Modelfile with that and tried to run? I tried different small variant of it but got core dump error even tho i have enough vram and llava 1.6 was easily runnable without issues even tho it was comparatively bigger in size, i created one issue recently regarding this #4925 .I thought multimodels are supported so download gguf files and created modelfile and tried to run but got some issues of which i posted logs on my issue which u can see. My question is does multimodels need explict support from ollama like specific variants can only run or what ? Pretty much confused right now :-))

@Greatz08 commented on GitHub (Jun 8, 2024): @kotaxyz did you tried to download gguf format files and create Modelfile with that and tried to run? I tried different small variant of it but got core dump error even tho i have enough vram and llava 1.6 was easily runnable without issues even tho it was comparatively bigger in size, i created one issue recently regarding this #4925 .I thought multimodels are supported so download gguf files and created modelfile and tried to run but got some issues of which i posted logs on my issue which u can see. My question is does multimodels need explict support from ollama like specific variants can only run or what ? Pretty much confused right now :-))

GiteaMirror commented

2026-04-12 13:32:01 -05:00

@kotaxyz commented on GitHub (Jun 8, 2024):

hi @HakaishinShwet yes , i downloaded the files ,and created the modelfiles 2 times one time the model was hallucinating on every image i give the second time it was working as a language model but no vision capabilities

@kotaxyz commented on GitHub (Jun 8, 2024): > @kotaxyz did you tried to download gguf format files and create Modelfile with that and tried to run? I tried different small variant of it but got core dump error even tho i have enough vram and llava 1.6 was easily runnable without issues even tho it was comparatively bigger in size, i created one issue recently regarding this #4925 .I thought multimodels are supported so download gguf files and created modelfile and tried to run but got some issues of which i posted logs on my issue which u can see. My question is does multimodels need explict support from ollama like specific variants can only run or what ? Pretty much confused right now :-)) hi @HakaishinShwet yes , i downloaded the files ,and created the modelfiles 2 times one time the model was hallucinating on every image i give the second time it was working as a language model but no vision capabilities

GiteaMirror commented

2026-04-12 13:32:02 -05:00

@Greatz08 commented on GitHub (Jun 8, 2024):

@kotaxyz did you use mmproj.F16.gguf file too while building model from Modelfile or forgot it? because without it even i can run standalone MiniCPM.gguf model but it wont act as multimodel but as chat only model.
When i tried building without mmproj.gguf it worked as chat model but with mmproj.gguf usage in building multimodel i faced issues as it was not running and showing errors which i mentioned in my issue number 4925

@Greatz08 commented on GitHub (Jun 8, 2024): @kotaxyz did you use mmproj.F16.gguf file too while building model from Modelfile or forgot it? because without it even i can run standalone MiniCPM.gguf model but it wont act as multimodel but as chat only model. When i tried building without mmproj.gguf it worked as chat model but with mmproj.gguf usage in building multimodel i faced issues as it was not running and showing errors which i mentioned in my issue number 4925

GiteaMirror commented

2026-04-12 13:32:02 -05:00

@kotaxyz commented on GitHub (Jun 8, 2024):

ah yes i was using only one model but i noticed that some people said its required to use both models in the modelfile but they also have been getting another type of error , thats why i was asking if this is official release from the people created ollama this at least will reduce the hassle and guarantee that it works for everyone , i don't want to get in the rabbit hole of me rebuilding the binaries

@kotaxyz commented on GitHub (Jun 8, 2024): > @kotaxyz did you use mmproj.F16.gguf file too while building model from Modelfile or forgot it? because without it even i can run standalone MiniCPM.gguf model but it wont act as multimodel but as chat only model. When i tried building without mmproj.gguf it worked as chat model but with mmproj.gguf usage in building multimodel i faced issues as it was not running and showing errors which i mentioned in my issue number 4925 ah yes i was using only one model but i noticed that some people said its required to use both models in the modelfile but they also have been getting another type of error , thats why i was asking if this is official release from the people created ollama this at least will reduce the hassle and guarantee that it works for everyone , i don't want to get in the rabbit hole of me rebuilding the binaries

GiteaMirror commented

2026-04-12 13:32:03 -05:00

@Greatz08 commented on GitHub (Jun 9, 2024):

@kotaxyz yea that's what i created issue for #4925 do check reply on it then u will understand why we getting error

@Greatz08 commented on GitHub (Jun 9, 2024): > > @kotaxyz did you use mmproj.F16.gguf file too while building model from Modelfile or forgot it? because without it even i can run standalone MiniCPM.gguf model but it wont act as multimodel but as chat only model. When i tried building without mmproj.gguf it worked as chat model but with mmproj.gguf usage in building multimodel i faced issues as it was not running and showing errors which i mentioned in my issue number 4925 > > ah yes i was using only one model but i noticed that some people said its required to use both models in the modelfile but they also have been getting another type of error , thats why i was asking if this is official release from the people created ollama this at least will reduce the hassle and guarantee that it works for everyone , i don't want to get in the rabbit hole of me rebuilding the binaries @kotaxyz yea that's what i created issue for #4925 do check reply on it then u will understand why we getting error

GiteaMirror commented

2026-04-12 13:32:04 -05:00

@kotaxyz commented on GitHub (Jun 9, 2024):

@GingerNg yup same here , tried 4 times always stuck

@kotaxyz commented on GitHub (Jun 9, 2024): > https://ollama.com/hhao/openbmb-minicpm-llama3-v-2_5 I tried to pull model, but failed many times, ![image](https://private-user-images.githubusercontent.com/13898738/337636364-aa2d21c3-2251-413b-a9e4-a0e5ed53ed03.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.FVBywkEfyvYZxvyaSw0054hFGqaw5zL4PQ0ihvUQgpI) @GingerNg yup same here , tried 4 times always stuck

GiteaMirror commented

2026-04-12 13:32:04 -05:00

@Greatz08 commented on GitHub (Jun 12, 2024):

@jmorganca any progress on this ? :-))

@Greatz08 commented on GitHub (Jun 12, 2024): @jmorganca any progress on this ? :-))

GiteaMirror commented

2026-04-12 13:32:05 -05:00

@kotaxyz commented on GitHub (Jun 19, 2024):

hi @jmorganca ,is there any plans to add this model

@kotaxyz commented on GitHub (Jun 19, 2024): hi @jmorganca ,is there any plans to add this model

GiteaMirror commented

2026-04-12 13:32:05 -05:00

@Milor123 commented on GitHub (Jul 4, 2024):

I have this error Error: llama runner process has terminated: signal: aborted (core dumped) in RTX 4070 12GB VRAM

ollama run hhao/openbmb-minicpm-llama3-v-2_5
pulling manifest 
pulling 391d11736c3c... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 1.0 GB                         
pulling 010ec3ba94cb... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 4.9 GB                         
pulling 8ab4849b038c... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏  254 B                         
pulling 2c527a8fcba5... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏  124 B                         
pulling ada64ec88682... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏  493 B                         
verifying sha256 digest 
writing manifest 
removing any unused layers 
success 
Error: llama runner process has terminated: signal: aborted (core dumped)

what should i do?

@Milor123 commented on GitHub (Jul 4, 2024): I have this error Error: llama runner process has terminated: signal: aborted (core dumped) in RTX 4070 12GB VRAM ``` ollama run hhao/openbmb-minicpm-llama3-v-2_5 pulling manifest pulling 391d11736c3c... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 1.0 GB pulling 010ec3ba94cb... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 4.9 GB pulling 8ab4849b038c... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 254 B pulling 2c527a8fcba5... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 124 B pulling ada64ec88682... 100% ▕██████████████████████████████████████████████████████████████████████████████████████████████████████████▏ 493 B verifying sha256 digest writing manifest removing any unused layers success Error: llama runner process has terminated: signal: aborted (core dumped) ``` what should i do?

GiteaMirror commented

2026-04-12 13:32:06 -05:00

@lstep commented on GitHub (Jul 8, 2024):

$ ollama -v
ollama version is 0.1.48

Trying to run hhao/openbmb-minicpm-llama3-v-2_5:q8_0, getting the following error: GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/examples/llava/clip.cpp:1024: new_clip->has_llava_projector

@lstep commented on GitHub (Jul 8, 2024): ``` $ ollama -v ollama version is 0.1.48 ``` Trying to run `hhao/openbmb-minicpm-llama3-v-2_5:q8_0`, getting the following error: `GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/examples/llava/clip.cpp:1024: new_clip->has_llava_projector`

GiteaMirror commented

2026-04-12 13:32:06 -05:00

@Forevery1 commented on GitHub (Jul 9, 2024):

At present, this model is not supported, but llama.cpp has a PR about this model

https://github.com/ggerganov/llama.cpp/pull/7599

@Forevery1 commented on GitHub (Jul 9, 2024): > ``` > $ ollama -v > ollama version is 0.1.48 > ``` > > Trying to run `hhao/openbmb-minicpm-llama3-v-2_5:q8_0`, getting the following error: `GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/examples/llava/clip.cpp:1024: new_clip->has_llava_projector` > > At present, this model is not supported, but llama.cpp has a PR about this model https://github.com/ggerganov/llama.cpp/pull/7599

GiteaMirror commented

2026-04-12 13:32:06 -05:00

@Milor123 commented on GitHub (Jul 9, 2024):

What is it? Can be used it with ollama like a vision??

@Milor123 commented on GitHub (Jul 9, 2024): > > ``` > > $ ollama -v > > ollama version is 0.1.48 > > ``` > > > > > > > > > > > > > > > > > > > > > > > > Trying to run `hhao/openbmb-minicpm-llama3-v-2_5:q8_0`, getting the following error: `GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/examples/llava/clip.cpp:1024: new_clip->has_llava_projector` > > At present, this model is not supported, but llama.cpp has a PR about this model > > [ggerganov/llama.cpp#7599](https://github.com/ggerganov/llama.cpp/pull/7599) What is it? Can be used it with ollama like a vision??

GiteaMirror commented

2026-04-12 13:32:06 -05:00

@lstep commented on GitHub (Jul 9, 2024):

Well, when llama.cpp will support it, yes. Vision is already supported on ollama, for supported LLMs, like moondream for example.

@lstep commented on GitHub (Jul 9, 2024): > > > ``` > > > $ ollama -v > > > ollama version is 0.1.48 > > > ``` > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > Trying to run `hhao/openbmb-minicpm-llama3-v-2_5:q8_0`, getting the following error: `GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/examples/llava/clip.cpp:1024: new_clip->has_llava_projector` > > > > > > At present, this model is not supported, but llama.cpp has a PR about this model > > [ggerganov/llama.cpp#7599](https://github.com/ggerganov/llama.cpp/pull/7599) > > What is it? Can be used it with ollama like a vision?? Well, when llama.cpp will support it, yes. Vision is already supported on ollama, for supported LLMs, like moondream for example.

GiteaMirror commented

2026-04-12 13:32:07 -05:00

@cmp-nct commented on GitHub (Jul 11, 2024):

moondream is currently not supported, the involved siglip-CLIP seems to not work correctly.

@cmp-nct commented on GitHub (Jul 11, 2024): > > > > ``` > > > > $ ollama -v > > > > ollama version is 0.1.48 > > > > ``` > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > Trying to run `hhao/openbmb-minicpm-llama3-v-2_5:q8_0`, getting the following error: `GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/examples/llava/clip.cpp:1024: new_clip->has_llava_projector` > > > > > > > > > At present, this model is not supported, but llama.cpp has a PR about this model > > > [ggerganov/llama.cpp#7599](https://github.com/ggerganov/llama.cpp/pull/7599) > > > > > > What is it? Can be used it with ollama like a vision?? > > Well, when llama.cpp will support it, yes. Vision is already supported on ollama, for supported LLMs, like moondream for example. moondream is currently not supported, the involved siglip-CLIP seems to not work correctly.

GiteaMirror commented

2026-04-12 13:32:07 -05:00

@lstep commented on GitHub (Jul 11, 2024):

What are you talking about??? moondream is officially supported, it is even in the official library (https://ollama.com/library/moondream). I've been using for months:

import (
        "context"
        "fmt"
        "log"
        "net/http"
        "net/url"
        "os"

        "github.com/ollama/ollama/api"
)

func main() {
        if len(os.Args) <= 1 {
                log.Fatal("usage: <image name>")
        }

        imgData, err := os.ReadFile(os.Args[1])
        if err != nil {
                log.Fatalf("error reading image file: %v", err)
        }

        clientURL, err := url.Parse("http://127.0.0.1:11434")
        if err != nil {
                log.Fatalf("error parsing client URL: %v", err)
        }

        client := api.NewClient(clientURL, http.DefaultClient)
        req := &api.GenerateRequest{
                Model:  "moondream:1.8b-v2-fp16",
                Prompt: "describe this image",
                Images: []api.ImageData{imgData},
        }

        ctx := context.Background()
        respFunc := func(resp api.GenerateResponse) error {
                fmt.Print(resp.Response)
                return nil
        }

        err = client.Generate(ctx, req, respFunc)
        if err != nil {
                log.Fatalf("error generating response: %v", err)
        }

        fmt.Println("A comment about life and its mysteries.")
}

$ ./gollama dog.png 

In the image, a large brown dog with shaggy fur is the main focus. The dog's tongue is out and its mouth appears slightly open, giving off an impression of relaxation or playfulness. The dog stands on all fours, facing to the right side of the image, creating a sense of curiosity about what it might be seeing or doing in that direction. The background features a grassy area dotted with trees, adding a touch of nature to the scene and providing a tranquil setting for this furry companion.A comment about life and its mysteries.

@lstep commented on GitHub (Jul 11, 2024): > > > > > ``` > > > > > $ ollama -v > > > > > ollama version is 0.1.48 > > > > > ``` > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > Trying to run `hhao/openbmb-minicpm-llama3-v-2_5:q8_0`, getting the following error: `GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/examples/llava/clip.cpp:1024: new_clip->has_llava_projector` > > > > > > > > > > > > At present, this model is not supported, but llama.cpp has a PR about this model > > > > [ggerganov/llama.cpp#7599](https://github.com/ggerganov/llama.cpp/pull/7599) > > > > > > > > > What is it? Can be used it with ollama like a vision?? > > > > > > Well, when llama.cpp will support it, yes. Vision is already supported on ollama, for supported LLMs, like moondream for example. > > moondream is currently not supported, the involved siglip-CLIP seems to not work correctly. What are you talking about??? moondream is officially supported, it is even in the official library (https://ollama.com/library/moondream). I've been using for months: ```go import ( "context" "fmt" "log" "net/http" "net/url" "os" "github.com/ollama/ollama/api" ) func main() { if len(os.Args) <= 1 { log.Fatal("usage: <image name>") } imgData, err := os.ReadFile(os.Args[1]) if err != nil { log.Fatalf("error reading image file: %v", err) } clientURL, err := url.Parse("http://127.0.0.1:11434") if err != nil { log.Fatalf("error parsing client URL: %v", err) } client := api.NewClient(clientURL, http.DefaultClient) req := &api.GenerateRequest{ Model: "moondream:1.8b-v2-fp16", Prompt: "describe this image", Images: []api.ImageData{imgData}, } ctx := context.Background() respFunc := func(resp api.GenerateResponse) error { fmt.Print(resp.Response) return nil } err = client.Generate(ctx, req, respFunc) if err != nil { log.Fatalf("error generating response: %v", err) } fmt.Println("A comment about life and its mysteries.") } ``` ![dog](https://github.com/user-attachments/assets/a8a281d5-5fd9-4814-9828-e9aa707518dc) ``` $ ./gollama dog.png In the image, a large brown dog with shaggy fur is the main focus. The dog's tongue is out and its mouth appears slightly open, giving off an impression of relaxation or playfulness. The dog stands on all fours, facing to the right side of the image, creating a sense of curiosity about what it might be seeing or doing in that direction. The background features a grassy area dotted with trees, adding a touch of nature to the scene and providing a tranquil setting for this furry companion.A comment about life and its mysteries. ```

GiteaMirror commented

2026-04-12 13:32:08 -05:00

@cmp-nct commented on GitHub (Jul 12, 2024):

What are you talking about??? moondream is officially supported, it is even in the official library (https://ollama.com/library/moondream). I've been using for months:

import (
        "context"
        "fmt"
        "log"
        "net/http"
        "net/url"
        "os"

        "github.com/ollama/ollama/api"
)

func main() {
        if len(os.Args) <= 1 {
                log.Fatal("usage: <image name>")
        }

        imgData, err := os.ReadFile(os.Args[1])
        if err != nil {
                log.Fatalf("error reading image file: %v", err)
        }

        clientURL, err := url.Parse("http://127.0.0.1:11434")
        if err != nil {
                log.Fatalf("error parsing client URL: %v", err)
        }

        client := api.NewClient(clientURL, http.DefaultClient)
        req := &api.GenerateRequest{
                Model:  "moondream:1.8b-v2-fp16",
                Prompt: "describe this image",
                Images: []api.ImageData{imgData},
        }

        ctx := context.Background()
        respFunc := func(resp api.GenerateResponse) error {
                fmt.Print(resp.Response)
                return nil
        }

        err = client.Generate(ctx, req, respFunc)
        if err != nil {
                log.Fatalf("error generating response: %v", err)
        }

        fmt.Println("A comment about life and its mysteries.")
}

$ ./gollama dog.png 

In the image, a large brown dog with shaggy fur is the main focus. The dog's tongue is out and its mouth appears slightly open, giving off an impression of relaxation or playfulness. The dog stands on all fours, facing to the right side of the image, creating a sense of curiosity about what it might be seeing or doing in that direction. The background features a grassy area dotted with trees, adding a touch of nature to the scene and providing a tranquil setting for this furry companion.A comment about life and its mysteries.

I'm sorry, I thought you mean moondream2. Which runs, but doesn't work properly (very poor quality).
I am not sure about moondream1, I recall I tested it and it did not work well on llama.cpp but that was many months ago.

@cmp-nct commented on GitHub (Jul 12, 2024): > > > > > > ``` > > > > > > $ ollama -v > > > > > > ollama version is 0.1.48 > > > > > > ``` > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > Trying to run `hhao/openbmb-minicpm-llama3-v-2_5:q8_0`, getting the following error: `GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/examples/llava/clip.cpp:1024: new_clip->has_llava_projector` > > > > > > > > > > > > > > > At present, this model is not supported, but llama.cpp has a PR about this model > > > > > [ggerganov/llama.cpp#7599](https://github.com/ggerganov/llama.cpp/pull/7599) > > > > > > > > > > > > What is it? Can be used it with ollama like a vision?? > > > > > > > > > Well, when llama.cpp will support it, yes. Vision is already supported on ollama, for supported LLMs, like moondream for example. > > > > > > moondream is currently not supported, the involved siglip-CLIP seems to not work correctly. > > What are you talking about??? moondream is officially supported, it is even in the official library (https://ollama.com/library/moondream). I've been using for months: > > ```go > import ( > "context" > "fmt" > "log" > "net/http" > "net/url" > "os" > > "github.com/ollama/ollama/api" > ) > > func main() { > if len(os.Args) <= 1 { > log.Fatal("usage: <image name>") > } > > imgData, err := os.ReadFile(os.Args[1]) > if err != nil { > log.Fatalf("error reading image file: %v", err) > } > > clientURL, err := url.Parse("http://127.0.0.1:11434") > if err != nil { > log.Fatalf("error parsing client URL: %v", err) > } > > client := api.NewClient(clientURL, http.DefaultClient) > req := &api.GenerateRequest{ > Model: "moondream:1.8b-v2-fp16", > Prompt: "describe this image", > Images: []api.ImageData{imgData}, > } > > ctx := context.Background() > respFunc := func(resp api.GenerateResponse) error { > fmt.Print(resp.Response) > return nil > } > > err = client.Generate(ctx, req, respFunc) > if err != nil { > log.Fatalf("error generating response: %v", err) > } > > fmt.Println("A comment about life and its mysteries.") > } > ``` > > ![dog](https://private-user-images.githubusercontent.com/2028/347962508-a8a281d5-5fd9-4814-9828-e9aa707518dc.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.X61yRKRJTcRG8IPo8tddnu3zaeR61DgAw_wwLnMw8RM) > > ``` > $ ./gollama dog.png > > In the image, a large brown dog with shaggy fur is the main focus. The dog's tongue is out and its mouth appears slightly open, giving off an impression of relaxation or playfulness. The dog stands on all fours, facing to the right side of the image, creating a sense of curiosity about what it might be seeing or doing in that direction. The background features a grassy area dotted with trees, adding a touch of nature to the scene and providing a tranquil setting for this furry companion.A comment about life and its mysteries. > ``` I'm sorry, I thought you mean moondream2. Which runs, but doesn't work properly (very poor quality). I am not sure about moondream1, I recall I tested it and it did not work well on llama.cpp but that was many months ago.

GiteaMirror commented

2026-04-12 13:32:08 -05:00

@lingyezhixing commented on GitHub (Aug 1, 2024):

Is the fit of this model progressing? Or do you have plans to adapt?

@lingyezhixing commented on GitHub (Aug 1, 2024): Is the fit of this model progressing? Or do you have plans to adapt?

GiteaMirror commented

2026-04-12 13:32:09 -05:00

@wlrnet commented on GitHub (Aug 13, 2024):

Distibution version macos app still not support this model, still need rebuild ./ollama binary file

@wlrnet commented on GitHub (Aug 13, 2024): Distibution version macos app still not support this model, still need rebuild ./ollama binary file

GiteaMirror referenced this issue

2026-04-12 23:20:01 -05:00

[PR #3094] [MERGED] Default Keep Alive environment variable #11065

GiteaMirror referenced this issue

2026-04-16 05:25:31 -05:00

[PR #3094] [MERGED] Default Keep Alive environment variable #16336

GiteaMirror referenced this issue

2026-04-19 15:44:32 -05:00

[PR #3094] [MERGED] Default Keep Alive environment variable #21605

GiteaMirror referenced this issue

2026-04-22 03:58:32 -05:00

[GH-ISSUE #2267] feat: Support ollama's keep_alive request parameter by overwriting with ENV on `ollama serve` #27062

GiteaMirror referenced this issue

2026-04-22 21:35:07 -05:00

[PR #3094] [MERGED] Default Keep Alive environment variable #36938

GiteaMirror referenced this issue

2026-04-24 22:05:22 -05:00

[PR #3094] [MERGED] Default Keep Alive environment variable #42313

GiteaMirror referenced this issue

2026-04-28 05:24:43 -05:00

[GH-ISSUE #2267] feat: Support ollama's keep_alive request parameter by overwriting with ENV on `ollama serve` #47814

GiteaMirror referenced this issue

2026-04-29 12:28:26 -05:00

[PR #3094] [MERGED] Default Keep Alive environment variable #57762

GiteaMirror referenced this issue

2026-05-03 13:03:11 -05:00

[GH-ISSUE #2267] feat: Support ollama's keep_alive request parameter by overwriting with ENV on `ollama serve` #63340

GiteaMirror referenced this issue

2026-05-05 05:09:28 -05:00

[PR #3094] [MERGED] Default Keep Alive environment variable #73359

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

hoyyeva/editor-config-repair

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

hoyyeva/launch-backup-ux

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-mlx-decode-checkpoints

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

brucemacd/download-before-remove

parth/update-claude-docs

parth-anthropic-reference-images-path

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#3094