github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10863] Model not found - Inconsistent API Behavior: api/generate fails over IPv6 localhost, while api/embeddings works. #53650

New Issue
Closed
opened 2026-04-29 04:22:59 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 04:22:59 -05:00
Owner
Copy Link

Originally created by @ppblaauw on GitHub (May 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10863

What is the issue?

I'm encountering an issue where the /api/generate endpoint for a text generation model (deepseek-r1:1.5b) consistently fails with a "model not found" error when accessed via http://localhost:11434 (which resolves to IPv6 ::1 on my system). However, the /api/embeddings endpoint for nomic-embed-text:latest works perfectly fine using the exact same http://localhost:11434 URL.

Crucially, both models and endpoints work correctly when accessed via http://127.0.0.1:11434 (IPv4) or when curl is explicitly forced to use IPv4 (-4 flag). This suggests a specific problem with how the /api/generate endpoint handles requests coming in over IPv6.

Steps to Reproduce:

1 Ensure Ollama server is running (e.g., ollama serve).

2 Pull the necessary models:

Bash

ollama pull deepseek-r1:1.5b
ollama pull nomic-embed-text:latest

3 Confirm deepseek-r1:1.5b works via CLI (expected to work):

Bash

ollama run deepseek-r1:1.5b "what model are you?"

4 Attempt to use api/generate with localhost (expected to fail):

Bash

curl http://localhost:11434/api/generate -d '{"model": "deepseek-r1:1.5b" , "prompt": " what model are you?" }' --verbose

5 Attempt to use api/embeddings with localhost (expected to work):

Bash

curl http://localhost:11434/api/embeddings -d '{ "model": "nomic-embed-text", "prompt": "The sky is blue because of Rayleigh scattering" }' --verbose

6 Attempt to use api/generate with 127.0.0.1 (expected to work):

Bash

curl http://127.0.0.1:11434/api/generate -d '{"model": "deepseek-r1:1.5b" , "prompt": " what model are you?" }'

7 Attempt to use api/generate with localhost and forced IPv4 (expected to work):

Bash

    curl -4 http://localhost:11434/api/generate -d '{"model": "deepseek-r1:1.5b" , "prompt": " what model are you?" }'

Expected Behavior:

All curl commands (Steps 4, 5, 6, 7) should successfully return a valid response from the Ollama server, including the api/generate request made via localhost.

Actual Behavior:

Step 4 (Fails): Returns {"error":"model 'deepseek-r1:1.5b' not found"} with an HTTP/1.1 404 Not Found status. The curl --verbose output confirms a successful connection to ::1 (IPv6).
Step 5 (Works): Returns a valid embedding. The curl --verbose output confirms a successful connection to ::1 (IPv6).
Step 6 (Works): Returns a valid text generation.
Step 7 (Works): Returns a valid text generation.

Diagnostic Information:

  ollama list output:

   NAME                         ID           SIZE      MODIFIED
   nomic-embed-text:latest      0a109f422b47 274 MB    6 hours ago
   deepseek-r1:1.5b             a42b25d8c10a 1.1 GB    4 months ago
   llama3.2:1b                  baf6a787fdff 1.3 GB    8 months ago
   llama3.2:latest              a80c4f17acd5 2.0 GB    8 months ago

    ping -a localhost output:

    Pinging DESKTOP-USER [::1] with 32 bytes of data:
    Reply from ::1: time<1ms
    Reply from ::1: time<1ms
    Reply from ::1: time<1ms
    Reply from ::1: time<1ms

Verbose output for failing api/generate call (Step 4):

    * Host localhost:11434 was resolved.
    * IPv6: ::1
    * IPv4: 127.0.0.1
    * Trying [::1]:11434...
    * Connected to localhost (::1) port 11434
    * using HTTP/1.x
    > POST /api/generate HTTP/1.1
    > Host: localhost:11434
    > User-Agent: curl/8.12.1
    > Accept: */*
    > Content-Length: 59
    > Content-Type: application/x-www-form-urlencoded
    >
    * upload completely sent off: 59 bytes
    < HTTP/1.1 404 Not Found
    < Content-Type: application/json; charset=utf-8
    < Date: Mon, 26 May 2025 09:31:27 GMT
    < Content-Length: 46
    <
    {"error":"model 'deepseek-r1:1.5b' not found"}* Connection #0 to host localhost left intact


Verbose output for working api/embeddings call (Step 5):

    * Host localhost:11434 was resolved.
    * IPv6: ::1
    * IPv4: 127.0.0.1
    * Trying [::1]:11434...
    * Connected to localhost (::1) port 11434
    * using HTTP/1.x
    > POST /api/embeddings HTTP/1.1
    > Host: localhost:11434
    > User-Agent: curl/8.12.1
    > Accept: */*
    > Content-Length: 91
    > Content-Type: application/x-www-form-urlencoded
    >
    * upload completely sent off: 91 bytes
    < HTTP/1.1 200 OK
    < Content-Type: application/json; charset=utf-8
    < Date: Mon, 26 May 2025 09:46:08 GMT
    < Transfer-Encoding: chunked
    < [rest of embedding response]

Environment:

Operating System: Windows 11
Ollama Version: 0.5.12

Relevant log output

OS

Windows

GPU

No response

CPU

Intel

Ollama version

0.5.12

Originally created by @ppblaauw on GitHub (May 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10863 ### What is the issue? I'm encountering an issue where the /api/generate endpoint for a text generation model (deepseek-r1:1.5b) consistently fails with a "model not found" error when accessed via http://localhost:11434 (which resolves to IPv6 ::1 on my system). However, the /api/embeddings endpoint for nomic-embed-text:latest works perfectly fine using the exact same http://localhost:11434 URL. Crucially, both models and endpoints work correctly when accessed via http://127.0.0.1:11434 (IPv4) or when curl is explicitly forced to use IPv4 (-4 flag). This suggests a specific problem with how the /api/generate endpoint handles requests coming in over IPv6. Steps to Reproduce: 1 Ensure Ollama server is running (e.g., ollama serve). 2 Pull the necessary models: ``` Bash ollama pull deepseek-r1:1.5b ollama pull nomic-embed-text:latest ``` 3 Confirm deepseek-r1:1.5b works via CLI (expected to work): ``` Bash ollama run deepseek-r1:1.5b "what model are you?" ``` 4 Attempt to use api/generate with localhost (expected to fail): ``` Bash curl http://localhost:11434/api/generate -d '{"model": "deepseek-r1:1.5b" , "prompt": " what model are you?" }' --verbose ``` 5 Attempt to use api/embeddings with localhost (expected to work): ``` Bash curl http://localhost:11434/api/embeddings -d '{ "model": "nomic-embed-text", "prompt": "The sky is blue because of Rayleigh scattering" }' --verbose ``` 6 Attempt to use api/generate with 127.0.0.1 (expected to work): ``` Bash curl http://127.0.0.1:11434/api/generate -d '{"model": "deepseek-r1:1.5b" , "prompt": " what model are you?" }' ``` 7 Attempt to use api/generate with localhost and forced IPv4 (expected to work): ``` Bash curl -4 http://localhost:11434/api/generate -d '{"model": "deepseek-r1:1.5b" , "prompt": " what model are you?" }' ``` Expected Behavior: All curl commands (Steps 4, 5, 6, 7) should successfully return a valid response from the Ollama server, including the api/generate request made via localhost. Actual Behavior: Step 4 (Fails): Returns {"error":"model 'deepseek-r1:1.5b' not found"} with an HTTP/1.1 404 Not Found status. The curl --verbose output confirms a successful connection to ::1 (IPv6). Step 5 (Works): Returns a valid embedding. The curl --verbose output confirms a successful connection to ::1 (IPv6). Step 6 (Works): Returns a valid text generation. Step 7 (Works): Returns a valid text generation. Diagnostic Information: ``` ollama list output: NAME ID SIZE MODIFIED nomic-embed-text:latest 0a109f422b47 274 MB 6 hours ago deepseek-r1:1.5b a42b25d8c10a 1.1 GB 4 months ago llama3.2:1b baf6a787fdff 1.3 GB 8 months ago llama3.2:latest a80c4f17acd5 2.0 GB 8 months ago ``` ``` ping -a localhost output: Pinging DESKTOP-USER [::1] with 32 bytes of data: Reply from ::1: time<1ms Reply from ::1: time<1ms Reply from ::1: time<1ms Reply from ::1: time<1ms ``` Verbose output for failing api/generate call (Step 4): ``` * Host localhost:11434 was resolved. * IPv6: ::1 * IPv4: 127.0.0.1 * Trying [::1]:11434... * Connected to localhost (::1) port 11434 * using HTTP/1.x > POST /api/generate HTTP/1.1 > Host: localhost:11434 > User-Agent: curl/8.12.1 > Accept: */* > Content-Length: 59 > Content-Type: application/x-www-form-urlencoded > * upload completely sent off: 59 bytes < HTTP/1.1 404 Not Found < Content-Type: application/json; charset=utf-8 < Date: Mon, 26 May 2025 09:31:27 GMT < Content-Length: 46 < {"error":"model 'deepseek-r1:1.5b' not found"}* Connection #0 to host localhost left intact ``` Verbose output for working api/embeddings call (Step 5): ``` * Host localhost:11434 was resolved. * IPv6: ::1 * IPv4: 127.0.0.1 * Trying [::1]:11434... * Connected to localhost (::1) port 11434 * using HTTP/1.x > POST /api/embeddings HTTP/1.1 > Host: localhost:11434 > User-Agent: curl/8.12.1 > Accept: */* > Content-Length: 91 > Content-Type: application/x-www-form-urlencoded > * upload completely sent off: 91 bytes < HTTP/1.1 200 OK < Content-Type: application/json; charset=utf-8 < Date: Mon, 26 May 2025 09:46:08 GMT < Transfer-Encoding: chunked < [rest of embedding response] ``` Environment: Operating System: Windows 11 Ollama Version: 0.5.12 ### Relevant log output ```shell ``` ### OS Windows ### GPU _No response_ ### CPU Intel ### Ollama version 0.5.12
GiteaMirror added the bug label 2026-04-29 04:22:59 -05:00
GiteaMirror commented 2026-04-29 04:23:03 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 26, 2025):

Server logs may aid in debugging.

What's the output of:

curl 'http://[::1]:11434/api/version'
curl 'http://[::1]:11434/api/tags'
curl 'http://127.0.0.1:11434/api/version'
curl 'http://127.0.0.1:11434/api/tags'
<!-- gh-comment-id:2909384051 --> @rick-github commented on GitHub (May 26, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging. What's the output of: ``` curl 'http://[::1]:11434/api/version' curl 'http://[::1]:11434/api/tags' curl 'http://127.0.0.1:11434/api/version' curl 'http://127.0.0.1:11434/api/tags' ```
GiteaMirror commented 2026-04-29 04:23:04 -05:00
Author
Owner
Copy Link

@ppblaauw commented on GitHub (May 26, 2025):

curl 'http://[::1]:11434/api/version'
{"version":"0.7.0"}

curl 'http://[::1]:11434/api/tags'  | jq
{
  "models": [
    {
      "name": "nomic-embed-text:latest",
      "model": "nomic-embed-text:latest",
      "modified_at": "2025-05-21T04:24:51.73054831Z",
      "size": 274302450,
      "digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "nomic-bert",
        "families": [
          "nomic-bert"
        ],
        "parameter_size": "137M",
        "quantization_level": "F16"
      }
    },
    {
      "name": "qwen2.5:7b-instruct-q4_K_M",
      "model": "qwen2.5:7b-instruct-q4_K_M",
      "modified_at": "2025-05-21T04:24:50.680466722Z",
      "size": 4683087332,
      "digest": "845dbda0ea48ed749caafd9e6037047aa19acfcfd82e704d7ca97d631a0b697e",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "qwen2",
        "families": [
          "qwen2"
        ],
        "parameter_size": "7.6B",
        "quantization_level": "Q4_K_M"
      }
    }
  ]
}

curl 'http://127.0.0.1:11434/api/version'
{"version":"0.5.12"}

curl -H "Accept: application/json" 'http://127.0.0.1:11434/api/tags'  | jq
{
  "models": [
    {
      "name": "deepseek-r1:1.5b",
      "model": "deepseek-r1:1.5b",
      "modified_at": "2025-05-26T14:50:59.5454808+08:00",
      "size": 1117322599,
      "digest": "a42b25d8c10a841bd24724309898ae851466696a7d7f3a0a408b895538ccbc96",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "qwen2",
        "families": [
          "qwen2"
        ],
        "parameter_size": "1.8B",
        "quantization_level": "Q4_K_M"
      }
    },
    {
      "name": "nomic-embed-text:latest",
      "model": "nomic-embed-text:latest",
      "modified_at": "2025-05-26T08:11:10.0245722+08:00",
      "size": 274302450,
      "digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "nomic-bert",
        "families": [
          "nomic-bert"
        ],
        "parameter_size": "137M",
        "quantization_level": "F16"
      }
    },
    {
      "name": "llama3.2:1b",
      "model": "llama3.2:1b",
      "modified_at": "2024-09-26T15:46:18.6438371+08:00",
      "size": 1321098329,
      "digest": "baf6a787fdffd633537aa2eb51cfd54cb93ff08e28040095462bb63daf552878",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "llama",
        "families": [
          "llama"
        ],
        "parameter_size": "1.2B",
        "quantization_level": "Q8_0"
      }
    },
    {
      "name": "llama3.2:latest",
      "model": "llama3.2:latest",
      "modified_at": "2024-09-26T15:25:03.773311+08:00",
      "size": 2019393189,
      "digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "llama",
        "families": [
          "llama"
        ],
        "parameter_size": "3.2B",
        "quantization_level": "Q4_K_M"
      }
    }
  ]
}

Thanks, that explains more

<!-- gh-comment-id:2909508015 --> @ppblaauw commented on GitHub (May 26, 2025): ``` curl 'http://[::1]:11434/api/version' {"version":"0.7.0"} curl 'http://[::1]:11434/api/tags' | jq { "models": [ { "name": "nomic-embed-text:latest", "model": "nomic-embed-text:latest", "modified_at": "2025-05-21T04:24:51.73054831Z", "size": 274302450, "digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f", "details": { "parent_model": "", "format": "gguf", "family": "nomic-bert", "families": [ "nomic-bert" ], "parameter_size": "137M", "quantization_level": "F16" } }, { "name": "qwen2.5:7b-instruct-q4_K_M", "model": "qwen2.5:7b-instruct-q4_K_M", "modified_at": "2025-05-21T04:24:50.680466722Z", "size": 4683087332, "digest": "845dbda0ea48ed749caafd9e6037047aa19acfcfd82e704d7ca97d631a0b697e", "details": { "parent_model": "", "format": "gguf", "family": "qwen2", "families": [ "qwen2" ], "parameter_size": "7.6B", "quantization_level": "Q4_K_M" } } ] } curl 'http://127.0.0.1:11434/api/version' {"version":"0.5.12"} curl -H "Accept: application/json" 'http://127.0.0.1:11434/api/tags' | jq { "models": [ { "name": "deepseek-r1:1.5b", "model": "deepseek-r1:1.5b", "modified_at": "2025-05-26T14:50:59.5454808+08:00", "size": 1117322599, "digest": "a42b25d8c10a841bd24724309898ae851466696a7d7f3a0a408b895538ccbc96", "details": { "parent_model": "", "format": "gguf", "family": "qwen2", "families": [ "qwen2" ], "parameter_size": "1.8B", "quantization_level": "Q4_K_M" } }, { "name": "nomic-embed-text:latest", "model": "nomic-embed-text:latest", "modified_at": "2025-05-26T08:11:10.0245722+08:00", "size": 274302450, "digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f", "details": { "parent_model": "", "format": "gguf", "family": "nomic-bert", "families": [ "nomic-bert" ], "parameter_size": "137M", "quantization_level": "F16" } }, { "name": "llama3.2:1b", "model": "llama3.2:1b", "modified_at": "2024-09-26T15:46:18.6438371+08:00", "size": 1321098329, "digest": "baf6a787fdffd633537aa2eb51cfd54cb93ff08e28040095462bb63daf552878", "details": { "parent_model": "", "format": "gguf", "family": "llama", "families": [ "llama" ], "parameter_size": "1.2B", "quantization_level": "Q8_0" } }, { "name": "llama3.2:latest", "model": "llama3.2:latest", "modified_at": "2024-09-26T15:25:03.773311+08:00", "size": 2019393189, "digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72", "details": { "parent_model": "", "format": "gguf", "family": "llama", "families": [ "llama" ], "parameter_size": "3.2B", "quantization_level": "Q4_K_M" } } ] } ``` Thanks, that explains more
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#53650
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?