[GH-ISSUE #10989] support for qwen3-embedding and qwen3-reranker models #69304

New Issue

GiteaMirror · 2026-05-04T17:44:13-05:00

GiteaMirror commented

2026-05-04 17:44:13 -05:00

Originally created by @pamdla on GitHub (Jun 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10989

Hi dear, please add these models, qwen3-embeddings, qwen3-rerankers , which are newly released on https://huggingface.co/Qwen/.

Originally created by @pamdla on GitHub (Jun 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10989 Hi dear, please add these models, qwen3-embeddings, qwen3-rerankers , which are newly released on https://huggingface.co/Qwen/.

GiteaMirror added the model label 2026-05-04 17:44:13 -05:00

GiteaMirror commented

2026-05-04 17:44:21 -05:00

@rick-github commented on GitHub (Jun 5, 2025):

ollama pull hf.co/Qwen/Qwen3-Embedding-0.6B-GGUF:Q8_0

ollama doesn't currently support ranking models, #3368.

@rick-github commented on GitHub (Jun 5, 2025): ``` ollama pull hf.co/Qwen/Qwen3-Embedding-0.6B-GGUF:Q8_0 ``` ollama doesn't currently support ranking models, #3368.

GiteaMirror commented

2026-05-04 17:44:23 -05:00

@pamdla commented on GitHub (Jun 5, 2025):

great, i made it.
however, reranker models are really helpful for rag, please make a plan for them.

@pamdla commented on GitHub (Jun 5, 2025): great, i made it. however, reranker models are really helpful for rag, please make a plan for them.

GiteaMirror commented

2026-05-04 17:44:24 -05:00

@chaorders1 commented on GitHub (Jun 6, 2025):

Looking forward Ollama support. This is the best embedding models. Waiting for years

@chaorders1 commented on GitHub (Jun 6, 2025): Looking forward Ollama support. This is the best embedding models. Waiting for years

GiteaMirror commented

2026-05-04 17:44:25 -05:00

@softlgl commented on GitHub (Jun 6, 2025):

I also hope to support qwen3-embedding

@softlgl commented on GitHub (Jun 6, 2025): I also hope to support qwen3-embedding

GiteaMirror commented

2026-05-04 17:44:25 -05:00

@hanwsf commented on GitHub (Jun 6, 2025):

Qwen embedding can support by Modelfile:
FROM /root/.ollama/Qwen3-Embedding-8B-Q4_K_M.gguf

SYSTEM """Qwen3-Embedding-8B 中文嵌入模型
向量维度: 4096
上下文长度: 32764
"""

TEMPLATE """{{ .Prompt }}"""
PARAMETER temperature 0

@hanwsf commented on GitHub (Jun 6, 2025): Qwen embedding can support by Modelfile: FROM /root/.ollama/Qwen3-Embedding-8B-Q4_K_M.gguf SYSTEM """Qwen3-Embedding-8B 中文嵌入模型向量维度: 4096 上下文长度: 32764 """ TEMPLATE """{{ .Prompt }}""" PARAMETER temperature 0

GiteaMirror commented

2026-05-04 17:44:26 -05:00

@rick-github commented on GitHub (Jun 6, 2025):

Just import it as show in https://github.com/ollama/ollama/issues/10989#issuecomment-2946454983.

@rick-github commented on GitHub (Jun 6, 2025): Just import it as show in https://github.com/ollama/ollama/issues/10989#issuecomment-2946454983.

GiteaMirror commented

2026-05-04 17:44:26 -05:00

@wwjCMP commented on GitHub (Jun 7, 2025):

Just import it as show in #10989 (comment).

Does ollama support changing the embedding length of embedding model?

@wwjCMP commented on GitHub (Jun 7, 2025): > Just import it as show in [#10989 (comment)](https://github.com/ollama/ollama/issues/10989#issuecomment-2946454983). Does ollama support changing the embedding length of embedding model?

GiteaMirror commented

2026-05-04 17:44:27 -05:00

@rick-github commented on GitHub (Jun 7, 2025):

No.

https://arxiv.org/abs/1708.03629

@rick-github commented on GitHub (Jun 7, 2025): No. https://arxiv.org/abs/1708.03629

GiteaMirror commented

2026-05-04 17:44:27 -05:00

@zcuder commented on GitHub (Jun 7, 2025):

@rick-github importing by the above modelfile doesn't show as embedding model, not sure if I need anything else in modelfile to make it work as expected

@zcuder commented on GitHub (Jun 7, 2025): @rick-github importing by the above modelfile doesn't show as embedding model, not sure if I need anything else in modelfile to make it work as expected

GiteaMirror commented

2026-05-04 17:44:28 -05:00

@rick-github commented on GitHub (Jun 7, 2025):

A model needs to have a pooling_type field in the KV metadata in order to have embedding as a listed capability. That's a part of the GGUF file, there's no Modelfile setting that can affect that. Note that any model can be used for embedding, models that have embedding as a capability are exclusively embedding models. In this case it looks like Qwen just took the embedding part of their general purpose model and made it available as a separate component. Because it doesn't have all the parameters of a general purpose model, it runs faster and takes less memory.

@rick-github commented on GitHub (Jun 7, 2025): A model needs to have a `pooling_type` field in the KV metadata in order to have `embedding` as a listed capability. That's a part of the GGUF file, there's no Modelfile setting that can affect that. Note that any model can be used for embedding, models that have `embedding` as a capability are exclusively embedding models. In this case it looks like Qwen just took the embedding part of their general purpose model and made it available as a separate component. Because it doesn't have all the parameters of a general purpose model, it runs faster and takes less memory.

GiteaMirror commented

2026-05-04 17:44:28 -05:00

@czadikem commented on GitHub (Jun 9, 2025):

Interested in seeing these models as official embedding models in the ollama model library sometime soon.

@czadikem commented on GitHub (Jun 9, 2025): Interested in seeing these models as official embedding models in the ollama model library sometime soon.

GiteaMirror commented

2026-05-04 17:44:28 -05:00

@GrainArc commented on GitHub (Jun 11, 2025):

What's funny is that previously, developers had implemented support for loading rerank models in Ollama through llama.cpp, but the official team refused to merge the code. Many people have raised the need for rerank model compatibility, but the official team has consistently turned a blind eye to it

@GrainArc commented on GitHub (Jun 11, 2025): What's funny is that previously, developers had implemented support for loading rerank models in Ollama through llama.cpp, but the official team refused to merge the code. Many people have raised the need for rerank model compatibility, but the official team has consistently turned a blind eye to it

GiteaMirror commented

2026-05-04 17:44:29 -05:00

@jessegross commented on GitHub (Jun 11, 2025):

@fmecool The original author never responded to comments on the code.

@jessegross commented on GitHub (Jun 11, 2025): @fmecool The original author never responded to comments on the code.

GiteaMirror commented

2026-05-04 17:44:29 -05:00

@yebanliuying commented on GitHub (Jun 12, 2025):

yep，we need it

@yebanliuying commented on GitHub (Jun 12, 2025): yep，we need it

GiteaMirror commented

2026-05-04 17:44:30 -05:00

@zcuder commented on GitHub (Jun 12, 2025):

@fmecool The original author never responded to comments on the code.

might be so many times back and forth and the author gave up this PR.
Could you guys make another one implementing this?

@zcuder commented on GitHub (Jun 12, 2025): > [@fmecool](https://github.com/fmecool) The original author never responded to comments on the code. might be so many times back and forth and the author gave up this PR. Could you guys make another one implementing this?

GiteaMirror commented

2026-05-04 17:44:31 -05:00

@Leroy-X commented on GitHub (Jun 18, 2025):

need+1

@Leroy-X commented on GitHub (Jun 18, 2025): need+1

GiteaMirror commented

2026-05-04 17:44:32 -05:00

@charescape commented on GitHub (Jun 19, 2025):

There are very few embedding models available for Ollama.

https://ollama.com/search?c=embedding

Embedding models are the type of models that Ollama needs to support the most.

@charescape commented on GitHub (Jun 19, 2025): There are very few embedding models available for Ollama. https://ollama.com/search?c=embedding Embedding models are the type of models that Ollama needs to support the most.

GiteaMirror commented

2026-05-04 17:44:32 -05:00

@GrainArc commented on GitHub (Jun 19, 2025):

Ollama has been compatible with embedding models since version 7.0, and the current focus is on the rerank model.

@GrainArc commented on GitHub (Jun 19, 2025): Ollama has been compatible with embedding models since version 7.0, and the current focus is on the rerank model.

GiteaMirror commented

2026-05-04 17:44:33 -05:00

@charescape commented on GitHub (Jun 19, 2025):

Since both models are widely needed, this issue can be divided into two PRs for Ollama:

one adding Qwen3-embedding model Support
and the other adding Qwen3-reranker model Support

@charescape commented on GitHub (Jun 19, 2025): Since both models are widely needed, this issue can be divided into two PRs for Ollama: - one adding **Qwen3-embedding model Support** - and the other adding **Qwen3-reranker model Support**

GiteaMirror commented

2026-05-04 17:44:33 -05:00

@rick-github commented on GitHub (Jun 19, 2025):

qwen3 embedding is already supported.

@rick-github commented on GitHub (Jun 19, 2025): qwen3 embedding is already supported.

GiteaMirror commented

2026-05-04 17:44:35 -05:00

@qwerty199369 commented on GitHub (Jun 27, 2025):

Rerank model support for Ollama:

PR open: https://github.com/ollama/ollama/pull/7219
PR closed: https://github.com/ollama/ollama/pull/11156

@qwerty199369 commented on GitHub (Jun 27, 2025): Rerank model support for Ollama: - PR open: https://github.com/ollama/ollama/pull/7219 - PR closed: https://github.com/ollama/ollama/pull/11156

GiteaMirror commented

2026-05-04 17:44:35 -05:00

@khanakia commented on GitHub (Jul 11, 2025):

qwen3 embedding is already supported.

it producing garbage not embedding. Can you tell me please how were you able to run it ?

  Qwen3-Embedding-8B-GGUF curl http://localhost:11434/api/generate -d '{
  "model": "hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest",
  "prompt":"hello"
}'
{"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:44.923137Z","response":"ค","done":false}
{"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:44.944965Z","response":":\r\n\r\n","done":false}
{"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:44.966548Z","response":"DAT","done":false}
{"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:44.988911Z","response":"dat","done":false}
{"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:45.011855Z","response":"OK","done":false}
{"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:45.034243Z","response":" day","done":false}

@khanakia commented on GitHub (Jul 11, 2025): > qwen3 embedding is already supported. it producing garbage not embedding. Can you tell me please how were you able to run it ? ``` Qwen3-Embedding-8B-GGUF curl http://localhost:11434/api/generate -d '{ "model": "hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest", "prompt":"hello" }' {"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:44.923137Z","response":"ค","done":false} {"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:44.944965Z","response":":\r\n\r\n","done":false} {"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:44.966548Z","response":"DAT","done":false} {"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:44.988911Z","response":"dat","done":false} {"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:45.011855Z","response":"OK","done":false} {"model":"hf.co/Qwen/Qwen3-Embedding-8B-GGUF:latest","created_at":"2025-07-11T08:11:45.034243Z","response":" day","done":false} ```

GiteaMirror commented

2026-05-04 17:44:36 -05:00

@rick-github commented on GitHub (Jul 11, 2025):

Use the /embed endpoint.

@rick-github commented on GitHub (Jul 11, 2025): Use the /embed endpoint.

GiteaMirror commented

2026-05-04 17:44:37 -05:00

@khanakia commented on GitHub (Jul 11, 2025):

@rick-github thanks it worked

Also, one more thing, do you know how I set the dimensions Qwen3-Embedding-8B-GGUF generates 4096 tokens currently i want only 1024

@khanakia commented on GitHub (Jul 11, 2025): @rick-github thanks it worked Also, one more thing, do you know how I set the `dimensions` `Qwen3-Embedding-8B-GGUF` generates 4096 tokens currently i want only `1024`

GiteaMirror commented

2026-05-04 17:44:38 -05:00

@rick-github commented on GitHub (Jul 11, 2025):

#11213

@rick-github commented on GitHub (Jul 11, 2025): #11213

GiteaMirror commented

2026-05-04 17:44:39 -05:00

@devlux76 commented on GitHub (Jul 14, 2025):

@rick-github thanks it worked

Also, one more thing, do you know how I set the dimensions Qwen3-Embedding-8B-GGUF generates 4096 tokens currently i want only 1024

It's MRL like nomic-embed-text this means you just truncate to the size you want since the most important vectors are first. I'm getting better results on Qwen3-0.6b embed truncated to 32 dimensions than I did on nomic-embed-text at 768 dimensions (or truncated). My use case is legal texts though so YMMV.

@devlux76 commented on GitHub (Jul 14, 2025): > [@rick-github](https://github.com/rick-github) thanks it worked > > Also, one more thing, do you know how I set the `dimensions` `Qwen3-Embedding-8B-GGUF` generates 4096 tokens currently i want only `1024` It's MRL like nomic-embed-text this means you just truncate to the size you want since the most important vectors are first. I'm getting better results on Qwen3-0.6b embed truncated to 32 dimensions than I did on nomic-embed-text at 768 dimensions (or truncated). My use case is legal texts though so YMMV.

GiteaMirror commented

2026-05-04 17:44:40 -05:00

@lianzhao commented on GitHub (Jul 15, 2025):

It's MRL like nomic-embed-text this means you just truncate to the size you want since the most important vectors are first. I'm getting better results on Qwen3-0.6b embed truncated to 32 dimensions than I did on nomic-embed-text at 768 dimensions (or truncated). My use case is legal texts though so YMMV.

Hello @devlux76, I was wondering if you could kindly clarify what exactly you were embedding? Were you embedding the user’s query, or the legal documents themselves? Thank you!

@lianzhao commented on GitHub (Jul 15, 2025): > It's MRL like nomic-embed-text this means you just truncate to the size you want since the most important vectors are first. I'm getting better results on Qwen3-0.6b embed truncated to 32 dimensions than I did on nomic-embed-text at 768 dimensions (or truncated). My use case is legal texts though so YMMV. Hello @devlux76, I was wondering if you could kindly clarify what exactly you were embedding? Were you embedding the user’s query, or the legal documents themselves? Thank you!

GiteaMirror commented

2026-05-04 17:44:41 -05:00

@devlux76 commented on GitHub (Jul 16, 2025):

It's MRL like nomic-embed-text this means you just truncate to the size you want since the most important vectors are first. I'm getting better results on Qwen3-0.6b embed truncated to 32 dimensions than I did on nomic-embed-text at 768 dimensions (or truncated). My use case is legal texts though so YMMV.

Hello @devlux76, I was wondering if you could kindly clarify what exactly you were embedding? Were you embedding the user’s query, or the legal documents themselves? Thank you!

I was embedding the documents for search with a clustering target and then generating embeddings for the query to perform a document search. The key here is that legal case texts have a very regular structure to them and need to cluster by more than simple semantic similarity since the laws of each jurisdiction are different and the overlap isn't very broad.

It's slow but works for the most part.

@devlux76 commented on GitHub (Jul 16, 2025): > > It's MRL like nomic-embed-text this means you just truncate to the size you want since the most important vectors are first. I'm getting better results on Qwen3-0.6b embed truncated to 32 dimensions than I did on nomic-embed-text at 768 dimensions (or truncated). My use case is legal texts though so YMMV. > > Hello [@devlux76](https://github.com/devlux76), I was wondering if you could kindly clarify what exactly you were embedding? Were you embedding the user’s query, or the legal documents themselves? Thank you! I was embedding the documents for search with a clustering target and then generating embeddings for the query to perform a document search. The key here is that legal case texts have a very regular structure to them and need to cluster by more than simple semantic similarity since the laws of each jurisdiction are different and the overlap isn't very broad. It's slow but works for the most part.

GiteaMirror commented

2026-05-04 17:44:42 -05:00

@kripper commented on GitHub (Aug 26, 2025):

ollama pull https://huggingface.co/Qwen/Qwen3-Embedding-4B-GGUF

@kripper commented on GitHub (Aug 26, 2025): `ollama pull https://huggingface.co/Qwen/Qwen3-Embedding-4B-GGUF`

GiteaMirror commented

2026-05-04 17:44:43 -05:00

@kripper commented on GitHub (Aug 26, 2025):

Mabye still broken?
https://github.com/ggml-org/llama.cpp/pull/14029

@kripper commented on GitHub (Aug 26, 2025): Mabye still broken? https://github.com/ggml-org/llama.cpp/pull/14029

GiteaMirror commented

2026-05-04 17:44:43 -05:00

@daniporr commented on GitHub (Sep 6, 2025):

The library includes several embedding models, such as https://ollama.com/library/granite-embedding and https://ollama.com/library/embeddinggemma. The latter is also featured in the latest release: https://github.com/ollama/ollama/releases/tag/v0.11.10

Why not include Qwen3 Embedding as well?

@daniporr commented on GitHub (Sep 6, 2025): The library includes several embedding models, such as https://ollama.com/library/granite-embedding and https://ollama.com/library/embeddinggemma. The latter is also featured in the latest release: https://github.com/ollama/ollama/releases/tag/v0.11.10 Why not include Qwen3 Embedding as well?

GiteaMirror commented

2026-05-04 17:44:44 -05:00

@rick-github commented on GitHub (Sep 24, 2025):

Now officially in the main library.

https://ollama.com/library/qwen3-embedding

@rick-github commented on GitHub (Sep 24, 2025): Now officially in the main library. https://ollama.com/library/qwen3-embedding

GiteaMirror commented

2026-05-04 17:44:45 -05:00

@ytwytw commented on GitHub (Sep 28, 2025):

Will ollama have reranker support?

@ytwytw commented on GitHub (Sep 28, 2025): Will ollama have reranker support?

GiteaMirror commented

2026-05-04 17:44:46 -05:00

@rick-github commented on GitHub (Sep 28, 2025):

https://github.com/ollama/ollama/pull/11389

@rick-github commented on GitHub (Sep 28, 2025): https://github.com/ollama/ollama/pull/11389

GiteaMirror commented

2026-05-04 17:44:48 -05:00

@PeterWang-dev commented on GitHub (Feb 17, 2026):

Any progress on this issue?

@PeterWang-dev commented on GitHub (Feb 17, 2026): Any progress on this issue?

GiteaMirror commented

2026-05-04 17:44:49 -05:00

@lyfuci commented on GitHub (Feb 17, 2026):

Any progress on this issue?

There doesn't seem to be a plan yet.

@lyfuci commented on GitHub (Feb 17, 2026): > Any progress on this issue? There doesn't seem to be a plan yet.

Sign in to join this conversation.

Branches Tags

main

parth-mlx-decode-checkpoints

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-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#69304