Skip to content

LLM Model Support List

The following summarizes the list of HuggingFace models supported by the current version of the LLM converter tool and their corresponding running commands (LLM converter will continue to expand the adaptation range).

Note

The following models all require the use of officially released pre-trained or quantized weights.

--all_fp16 parameter is used for full FP16 conversion of non-AWQ/GPTQ models. It bypasses the quantization library and can directly generate offline models, but with lower inference speed and efficiency.

It is recommended to prioritize quantized weights such as AWQ/GPTQ to ensure the performance and efficiency of the converted model.

โš ๏ธ [Version Dependency Specification]

Component Required Version
LLM_Converter Based on transformers 4.57.3
Input Model Must be an HF model trained with transformer 4.57.3

๐Ÿ“Š Supported Model List

Update Time: 2025-01-09

Total Models: 34

Model Series Version Model Link
DeepSeek_R1 1.5B https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
DeepSeek Janus Pro 1B https://huggingface.co/deepseek-ai/Janus-Pro-1B
Qwen2.5 0.5B https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct-AWQ
1.5B https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-AWQ
1.5B-Int4 https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-AWQ
1.5B-Int4 https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4
1.5B-Int8 https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int8
3B https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-AWQ
Qwen3 0.6B https://huggingface.co/Qwen/Qwen3-0.6B
1.7B https://huggingface.co/Qwen/Qwen3-1.7B
4B https://huggingface.co/Qwen/Qwen3-4B
Qwen2.5-VL 3B https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct
Qwen2.5-Omni 3B https://huggingface.co/Qwen/Qwen2.5-Omni-3B
Qwen3-VL 2B https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct
opus-mt-zh-en 140M https://huggingface.co/Helsinki-NLP/opus-mt-zh-en
InternVL2.5-MP0 1B https://huggingface.co/OpenGVLab/InternVL2_5-1B-MPO
2B https://huggingface.co/OpenGVLab/InternVL2_5-2B-MPO
InternVL2.5 1B https://huggingface.co/OpenGVLab/InternVL2_5-1B
2B https://huggingface.co/OpenGVLab/InternVL2_5-2B
Gemma 2B https://huggingface.co/google/gemma-2b
Gemma2 2B https://huggingface.co/google/gemma-2-2b-it
Gemma3 1B https://huggingface.co/google/gemma-3-1b-it
Llama 3.2 1B https://huggingface.co/meta-llama/Llama-3.2-1B
3B https://huggingface.co/meta-llama/Llama-3.2-3B
Phi 3 Mini 3.8B https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
Phi 4 Mini 3.8B https://huggingface.co/microsoft/Phi-4-mini-instruct
MiniMind2 104M https://huggingface.co/jingyaogong/MiniMind2
MiniMind2-V 104M https://huggingface.co/jingyaogong/MiniMind2-V
Florence-2-base 0.2B https://huggingface.co/florence-community/Florence-2-base
SmolVLM-256M 256M https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct
SmolVLM2-500M 500M https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct
FastVLM 0.5B https://huggingface.co/apple/FastVLM-0.5B
FastVLM 1.5B https://huggingface.co/apple/FastVLM-1.5B
whisper-tiny 37.8M https://huggingface.co/openai/whisper-tiny

๐Ÿ“‹ Model Classification

DeepSeek_R1

โœ… 1.5B

Practice

  • Conversion command reference:
python3 convert_hf_to_sim.py \
-d /path/to/model/ \
-o /path/to/output_model/ \
--inputs /path/to/input.json \
--soc_version CHIP
  • For input.json construction method, please refer to the Constructing Quantization Calibration Data section in "SGS Quantized Model Conversion" chapter of Quick Start.

  • Running command reference:

python3 run_llm.py \
-d /path/to/output_model/ \
--prompt "Give me a short introduction to large language model." \
--soc_version CHIP

DeepSeek Janus Pro

โœ… 1B

โš ๏ธ Currently only Image-to-Text quantization is supported. Text-to-Image is not yet supported.

Practice

  • Conversion command reference:
python3 convert_hf_to_sim.py \
-d /path/to/model/ \
-o /path/to/output_model/ \
--inputs /path/to/input.json \
--visual_input_formats YUV_NV12 \
--soc_version CHIP
  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command reference:

python3 run_llm.py \
-d /path/to/output_model/ \
-t /path/to/model/ \
--image /path/to/jpg/ \
--no_streamer \
--prompt "Please describe this image" \
--soc_version CHIP

Qwen2.5

โœ… 0.5B

โœ… 1.5B

โœ… 1.5B-Int4

โœ… 1.5B-Int4

โœ… 1.5B-Int8

โœ… 3B

Practice

  • Conversion command reference (AWQ/GPTQ models do not require --inputs parameter):

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --soc_version CHIP
    

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model." \
    --soc_version CHIP
    

Qwen3

โœ… 0.6B

โœ… 1.7B

โœ… 4B

Practice

  • Conversion command reference:
python3 convert_hf_to_sim.py \
-d /path/to/model/ \
-o /path/to/output_model/ \
--inputs /path/to/input.json \
--soc_version CHIP
  • For input.json construction method, please refer to the Constructing Quantization Calibration Data section in "SGS Quantized Model Conversion" chapter of Quick Start.

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model." \
    --soc_version CHIP
    

Qwen2.5-VL

โœ… 3B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --imgsz 672 392  --n_tokens 512 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --image /path/to/jpg/ \
    --processor_decode
    --no_streamer \
    --prompt "Please describe this image" \
    --soc_version CHIP
    

Qwen2.5-Omni

โœ… 3B

โš ๏ธ SGS quantization is not yet supported.

Practice

  • Conversion command reference:

    python3 ./convert_hf_to_sim.py \
    -d /path/to/model/
    --n_tokens 64 \
    --imgsz 224 224 \
    --videosz 8 3 308 308 \
    --soc_version CHIP
    

  • Running command reference:

    python3 ./run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Describe the input" \
    --image /path/to/image/ \
    --video /path/to/video/ \
    --wav_file /path/to/wav/ \
    --use_audio_in_video \
    --soc_version CHIP
    

Qwen3-VL

โœ… 2B

Practice

  • Conversion command reference:

    python3 ../Tool/Scripts/LLM_Converter/convert_hf_to_sim.py \
        -d /path/to/Qwen/Qwen3-VL-2B-Instruct/ \
        -o output_models \
        --visual_input_formats YUV_NV12 \
        --imgsz 384 384 \
        --videosz 8 3 384 384 \
        --num_soc 2 \
        --inputs inputs.json
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command reference:

    python3 ../Tool/Scripts/LLM_Converter/run_llm.py \
        -t /path/to/Qwen/Qwen3-VL-2B-Instruct/ \
        -d output_models \
        --prompt "Briefly describe this image" \
        --image /path/to/image.jpg \
        --soc_version CHIP
    

opus-mt-zh-en

โœ… 140M

Practice

  • Conversion command:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs input.json \
    -q Q15 Q10 Q25 \
    --max_length 512 \
    --encoder_tokens 128 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {"prompt": "ไธญๅ›ฝๅ››ๅคงๅ่‘—ๆœ‰ๅ“ชไบ›๏ผŸ"},
        {"prompt": "่ฏท็”Ÿๆˆไธ€ๆฎต็ง‘ๆŠ€ๆ–น้ข็š„ๆ–‡ๆœฌ๏ผŒ512ไธชๅญ—ใ€‚"},
        {"prompt": "5+8*10็š„็ป“ๆžœๆ˜ฏ๏ผŸ"},
        {"prompt": "่ฏทๅฐ†ๅฆ‚ไธ‹ไธญๆ–‡็ฟป่ฏ‘ไธบ่‹ฑๆ–‡๏ผšๆœ‰ๆœ‹่‡ช่ฟœๆ–นๆฅ๏ผŒไธไบฆไนไนŽใ€‚"}
    ]
    

  • Running command:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --no_streamer \
    --prompt "ไฝ ๅฅฝ๏ผŒๆˆ‘ๆ˜ฏไธญๅ›ฝไบบ๏ผ" \
    --soc_version CHIP
    

InternVL2.5-MP0

โœ… 1B

Practice

  • Conversion command:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --image /path/to/jpg/ \
    --prompt "Please describe this image" \
    --soc_version CHIP
    

โœ… 2B

Practice

  • Conversion command:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --image /path/to/jpg/ \
    --prompt "Please describe this image" \
    --soc_version CHIP
    

InternVL2.5

โœ… 1B

โœ… 2B

Practice

  • Conversion command:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --image /path/to/jpg/ \
    --prompt "Please describe this image" \
    --soc_version CHIP
    

Gemma

โœ… 2B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --soc_version CHIP
    

  • For input.json construction method, please refer to the Constructing Quantization Calibration Data section in "SGS Quantized Model Conversion" chapter of Quick Start.

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model." \
    --soc_version CHIP
    

Gemma2

โœ… 2B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --soc_version CHIP
    

  • For input.json construction method, please refer to the Constructing Quantization Calibration Data section in "SGS Quantized Model Conversion" chapter of Quick Start.

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model." \
    --soc_version CHIP
    

Gemma3

โœ… 1B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --soc_version CHIP
    

  • For input.json construction method, please refer to the Constructing Quantization Calibration Data section in "SGS Quantized Model Conversion" chapter of Quick Start.

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model." \
    --soc_version CHIP
    

Llama 3.2

โœ… 1B

โœ… 3B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --soc_version CHIP
    

  • For input.json construction method, please refer to the Constructing Quantization Calibration Data section in "SGS Quantized Model Conversion" chapter of Quick Start.

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model." \
    --soc_version CHIP
    

Phi 3 Mini

โœ… 3.8B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --soc_version CHIP
    

  • For input.json construction method, please refer to the Constructing Quantization Calibration Data section in "SGS Quantized Model Conversion" chapter of Quick Start.

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model." \
    --soc_version CHIP
    

Phi 4 Mini

โœ… 3.8B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --soc_version CHIP
    

  • For input.json construction method, please refer to the Constructing Quantization Calibration Data section in "SGS Quantized Model Conversion" chapter of Quick Start.

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model." \
    --soc_version CHIP
    

MiniMind2

โœ… 104M

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --soc_version CHIP
    

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --prompt "Give me a short introduction to large language model."
    

MiniMind2-V

โœ… 104M

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model/ \
    -o /path/to/output_model/ \
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model/ \
    --image /path/to/demo.jpg \
    --prompt "Describe this image shortly." \
    --soc_version CHIP
    

Florence-2-base

โœ… 0.2B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model \
    -o /path/to/output_model \
    --inputs /path/to/input.json  \
    --visual_input_formats YUV_NV12 \
    -q Q15 Q10 Q25 Q25 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {"prompt": "<OD>", "image": "/path/to/image.jpg"},
        {"prompt": "<CAPTION>", "image": "/path/to/image.jpg"}
    ]
    

  • Running command reference:

    python3  run_llm.py \
    -d /path/to/output_model \
    --prompt "<OD>" \
    --image /path/to/image \
    --no_streamer \
    --processor_postprocess_generate \
    --processor_decode \
    --soc_version CHIP
    

SmolVLM-256M

โœ… 256M

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model \
    -o /path/to/output_model \
    --n_tokens 2048 \
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model \
    -t /path/to/model \
    --image /path/to/demo.jpg \
    --prompt "Describe this image shortly." \
    --no_streamer \
    --soc_version CHIP
    

SmolVLM2-500M

โœ… 500M

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model \
    -o /path/to/output_model \
    --n_tokens 2048 \
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model \
    -t /path/to/model \
    --image /path/to/demo.jpg \
    --prompt "Describe this image shortly." \
    --no_streamer \
    --soc_version CHIP
    

FastVLM

โœ… 0.5B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model \
    -o /path/to/output_model \
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --max_length 512 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model \
    -t /path/to/model \
    --image /path/to/demo.jpg \
    --prompt "Describe this image shortly." \
    --no_streamer \
    --soc_version CHIP
    

โœ… 1.5B

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model \
    -o /path/to/output_model \
    --inputs /path/to/input.json \
    --visual_input_formats YUV_NV12 \
    --max_length 512 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {
            "prompt": "Briefly describe this image",
            "image": "/path/to/image.jpg"
        }
    ]
    

  • Running command reference:

    python3 run_llm.py \
    -d /path/to/output_model \
    -t /path/to/model \
    --image /path/to/demo.jpg \
    --prompt "Describe this image shortly." \
    --no_streamer \
    --soc_version CHIP
    

whisper-tiny

โœ… 37.8M

Practice

  • Conversion command reference:

    python3 convert_hf_to_sim.py \
    -d /path/to/model \
    -o /path/to/output_model \
    --inputs /path/to/input.json \
    -q Q15 Q10 Q25 \
    --max_length 512 \
    --soc_version CHIP
    

  • input.json format example:

    [
        {"prompt": null, "wav_file": ["/path/to/new.wav"]},
        {"prompt": null, "wav_file": ["/path/to/take_photo.wav"]}
    ]
    

  • Running command reference:

    python3  run_llm.py \
    -d /path/to/output_model \
    --wav_file /path/to/wav \
    --no_streamer \
    --host 10.44.16.18  \
    --port  3333 \
    --model_onboard_dir /path/to/board \
    --soc_version CHIP