--- title: DeepSeek-R1-MXFP4-ASQ canonical_url: "https://www.modelscope.ai/models/AMD/DeepSeek-R1-MXFP4-ASQ" md_url: "https://www.modelscope.ai/models/AMD/DeepSeek-R1-MXFP4-ASQ.md" repository: AMD/DeepSeek-R1-MXFP4-ASQ last_updated: 2026-01-05 license: mit model_type: - deepseek_v3 architectures: - DeepseekV3ForCausalLM base_model: - deepseek-ai/DeepSeek-R1 base_model_relation: quantized parameters: 362.8B tensor_type: - U8 - BF16 library_name: - safetensors - pytorch frameworks: - pytorch downloads: 126 stars: 0 --- # DeepSeek-R1-MXFP4-ASQ > DeepSeek-R1-MXFP4-ASQ - An open-source model by AMD on ModelScope. Model Architecture: DeepSeek-R1 Input: Text Output: Text Supported Hardware Microarchitecture: AMD MI350/MI355 ROCm: 7.0 PyTorch: 2.8.0 Transformers: 4.53.0 Operating System(s): Linux… AMD/DeepSeek-R1-MXFP4-ASQ is a 362.8B-parameter machine learning model on ModelScope. licensed under mit. derived from deepseek-ai/DeepSeek-R1. - **Repository**: AMD/DeepSeek-R1-MXFP4-ASQ - **License**: mit - **Parameters**: 362.8B - **Base model**: deepseek-ai/DeepSeek-R1 - **Downloads**: 126 - **Stars**: 0 - **Last updated**: 2026-01-05 Source: https://www.modelscope.ai/models/AMD/DeepSeek-R1-MXFP4-ASQ --- # Model Overview - **Model Architecture:** DeepSeek-R1 - **Input:** Text - **Output:** Text - **Supported Hardware Microarchitecture:** AMD MI350/MI355 - **ROCm**: 7.0 - **PyTorch**: 2.8.0 - **Transformers**: 4.53.0 - **Operating System(s):** Linux - **Inference Engine:** [SGLang](https://docs.sglang.ai/) - **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (V0.10) - **Weight quantization:** OCP MXFP4, Static - **Activation quantization:** OCP MXFP4, Dynamic - **Calibration Dataset:** [Pile](https://huggingface.co/datasets/mit-han-lab/pile-val-backup) This model was built with deepseek-ai DeepSeek-R1 model by applying [AMD-Quark](https://quark.docs.amd.com/latest/index.html) for MXFP4 quantization. # Model Quantization The model was quantized from [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) using [AMD-Quark](https://quark.docs.amd.com/latest/index.html). Both weights and activations were quantized to MXFP4 format, and the AutoSmoothQuant algorithm was applied to enhance accuracy. **Preprocessing requirement:** Before executing the quantization script below, the original FP8 model must first be dequantized to BFloat16. You can either perform the dequantization manually using this [conversion script](https://github.com/deepseek-ai/DeepSeek-V3/blob/main/inference/fp8_cast_bf16.py), or use the pre-converted BFloat16 model available at [unsloth/DeepSeek-R1-BF16](https://huggingface.co/unsloth/DeepSeek-R1-BF16). **Quantization scripts:** ``` cd Quark/examples/torch/language_modeling/llm_ptq/ exclude_layers="*self_attn* *mlp.gate.* *lm_head" python3 quantize_quark.py --model_dir $MODEL_DIR \ --quant_scheme w_mxfp4_a_mxfp4 \ --group_size 32 \ --num_calib_data 128 \ --exclude_layers $exclude_layers \ --skip_evaluation \ --multi_gpu \ --quant_algo autosmoothquant \ --model_export hf_format \ --output_dir amd/DeepSeek-R1-MXFP4-ASQ ``` # Deployment ### Use with SGLang This model can be deployed efficiently using the [SGLang](https://docs.sglang.ai/) backend. ## Evaluation The model was evaluated on reasoning tasks including AIME24, MMLU_COT, and GSM8K via [forked lm-evaluation-harness](https://github.com/BowenBao/lm-evaluation-harness/tree/cot) . ### Accuracy
Benchmark DeepSeek-R1 DeepSeek-R1-MXFP4-ASQ(this model) Recovery
AIME24 78.0 76.0 97.44%
MMLU_COT 79.90 79.65 99.69%
GSM8K 95.81 95.42 99.59%
### Reproduction The results of AIME24 and MMLU_COT were obtained using [SGLang](https://docs.sglang.ai/) while result of GSM8K was obtained using [vLLM](https://docs.vllm.ai/en/latest/). All the evaluations were conducted via forked [lm-evaluation-harness](https://github.com/BowenBao/lm-evaluation-harness/tree/cot). ### AIME24 ``` # Launching server python3 -m sglang.launch_server \ --model amd/DeepSeek-R1-MXFP4-ASQ \ --tp 8 \ --trust-remote-code \ --n-share-experts-fusion 8 \ --disable-radix-cache # Evaluating lm_eval --model local-completions \ --model_args model=amd/DeepSeek-R1-MXFP4-ASQ,base_url=http://localhost:30000/v1/completions,num_concurrent=999999,timeout=999999,tokenized_requests=False,max_length=32000,temperature=0.6,top_p=0.95 \ --tasks aime24 \ --num_fewshot 0 \ --gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,max_tokens=32000" \ --batch_size auto \ --log_samples \ --output_path output_data/aime24 2>&1 | tee logs/aime24.log ``` ### MMLU_COT ``` # Launching server python3 -m sglang.launch_server \ --model amd/DeepSeek-R1-MXFP4-ASQ \ --tp 8 \ --trust-remote-code \ --chunked-prefill-size 32768 \ --mem-fraction-static 0.83 # Evaluating lm_eval --model local-completions \ --model_args model=amd/DeepSeek-R1-MXFP4-ASQ,base_url=http://localhost:30000/v1/completions,num_concurrent=999999,timeout=999999,tokenized_requests=False,max_length=32000,temperature=0.6,top_p=0.95 \ --tasks mmlu_cot \ --num_fewshot 0 \ --gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,max_tokens=32000" \ --batch_size auto \ --log_samples \ --output_path output_data/mmmlu_cot 2>&1 | tee logs/mmmlu_cot.log ``` ### GSM8K ``` lm_eval --model local-completions \ --model_args model=amd/DeepSeek-R1-MXFP4-ASQ,base_url=http://localhost:30000/v1/completions,num_concurrent=999999,timeout=999999,tokenized_requests=False,max_length=8096 \ --tasks gsm8k \ --num_fewshot 5 \ --batch_size auto \ --log_samples \ --output_path output_data/gsm8k 2>&1 | tee logs/gsm8k.log ``` # License Modifications Copyright(c) 2025 Advanced Micro Devices, Inc. All rights reserved.