You can deploy this model and start earning money today!

amd/
Kimi-K2.6-MXFP4

Name: Kimi-K2.6-MXFP4
Availability: InStock

Views

No views yet

Model Overview

Model Architecture: Kimi-K2.6
- Input: Text, Image, Video
- Output: Text
Supported Hardware Microarchitecture: AMD MI350/MI355
ROCm: 7.2.0
PyTorch: 2.9.1
Transformers: 5.8.1
Operating System(s): Linux
Inference Engine: SGLang/vLLM
Model Optimizer: AMD-Quark (v0.11.1)
- Quantized layers: experts, shared_experts
- Weight quantization: OCP MXFP4, Static
- Activation quantization: OCP MXFP4, Dynamic

This model was built with Kimi-K2.6 model by applying AMD-Quark for MXFP4 quantization.

Model Quantization

The model was quantized from a BF16-decompressed version of moonshotai/Kimi-K2.6 using AMD-Quark. The original checkpoint uses native INT4 (compressed-tensors) quantization; it was first decompressed to BF16 before applying MXFP4 quantization. The weights and activations are quantized to MXFP4.

Quantization scripts:

cd Quark/examples/torch/language_modeling/llm_ptq/
exclude_layers="*self_attn* *mlp.gate *lm_head *mm_projector* *vision_tower*"

python quantize_quark.py \
    --model_dir /path/to/Kimi-K2.6-bf16 \
    --quant_scheme mxfp4 \
    --exclude_layers $exclude_layers \
    --output_dir amd/Kimi-K2.6-MXFP4 \
    --model_export hf_format \
    --file2file_quantization

Deployment

Use with vLLM/SGLang

This model can be deployed efficiently using the vLLM and SGLang backends.

Evaluation

The model was evaluated on gsm8k benchmarks using the vllm framework.

Accuracy

Benchmark	Kimi-K2.6	Kimi-K2.6-MXFP4 (this model)	Recovery
GSM8K (flexible-extract)	93.93	93.25	99.3%

Reproduction

The GSM8K results were obtained using the vLLM framework, based on the Docker image rocm/vllm-dev:nightly_main_20260417, with lm-eval and amd-quark compiled and installed from source, and vLLM (version 0.19.1rc1.dev369+gb1dc87a09) pre-installed in the docker image.

lm_eval \
  --model vllm \
  --model_args pretrained=amd/Kimi-K2.6-MXFP4,trust_remote_code=True,tensor_parallel_size=4 \
  --tasks gsm8k \
  --batch_size auto

amd/Kimi-K2.6-MXFP4