amd / Kimi-K2.5-MXFP4

huggingface.co
Total runs: 52.2K
24-hour runs: -1.1K
7-day runs: -7.1K
30-day runs: 71
Model's Last Updated: July 01 2026

Introduction of Kimi-K2.5-MXFP4

Model Details of Kimi-K2.5-MXFP4

Model Overview

  • Model Architecture: Kimi-K2.5
    • Input: Text
    • Output: Text
  • Supported Hardware Microarchitecture: AMD MI350/MI355
  • ROCm: 7.1.0
  • Operating System(s): Linux
  • Inference Engine: vLLM
  • Model Optimizer: AMD-Quark
    • Weight quantization: MOE-only, OCP MXFP4, Static
    • Activation quantization: MOE-only, OCP MXFP4, Dynamic
  • Calibration Dataset: Pile

This model was built with Kimi-K2.5 model by applying AMD-Quark for MXFP4 quantization.

Model Quantization

The model was quantized from moonshotai/Kimi-K2.5 using AMD-Quark . The weights and activations are quantized to MXFP4.

Deployment

Use with vLLM

This model can be deployed efficiently using the vLLM backend.

Evaluation

The model was evaluated on GSM8K benchmarks.

Accuracy
Benchmark Kimi-K2.5 Kimi-K2.5-MXFP4(this model) Recovery
GSM8K (flexible-extract) 94.09 93.25 99.1%
Reproduction

The GSM8K results were obtained using the lm-evaluation-harness framework, based on the Docker image vllm/vllm-openai-rocm:v0.14.0 .

Install the vLLM (commit 05339a7b207e2f32b56c29398c18d577c74cef3b) and lm-eval (Version: 0.4.10) in container first.

git clone https://github.com/vllm-project/vllm.git
cd vllm
python3 setup.py develop

pip install lm-eval
Launching server
vllm serve amd/Kimi-K2.5-MXFP4 -tp 4 \
  --mm-encoder-tp-mode data \
  --tool-call-parser kimi_k2 \
  --reasoning-parser kimi_k2 \
  --trust-remote-code \
  --enforce-eager
Evaluating model in a new terminal
lm_eval \
  --model local-completions \
  --model_args "model=amd/Kimi-K2.5-MXFP4,base_url=http://0.0.0.0:8000/v1/completions,tokenized_requests=False,tokenizer_backend=None,num_concurrent=32" \
  --tasks gsm8k \
  --num_fewshot 5 \
  --batch_size 1

License

Modifications Copyright(c) 2025 Advanced Micro Devices, Inc. All rights reserved.

Runs of amd Kimi-K2.5-MXFP4 on huggingface.co

52.2K
Total runs
-1.1K
24-hour runs
-4.6K
3-day runs
-7.1K
7-day runs
71
30-day runs

More Information About Kimi-K2.5-MXFP4 huggingface.co Model

More Kimi-K2.5-MXFP4 license Visit here:

https://choosealicense.com/licenses/modified-mit

Kimi-K2.5-MXFP4 huggingface.co

Kimi-K2.5-MXFP4 huggingface.co is an AI model on huggingface.co that provides Kimi-K2.5-MXFP4's model effect (), which can be used instantly with this amd Kimi-K2.5-MXFP4 model. huggingface.co supports a free trial of the Kimi-K2.5-MXFP4 model, and also provides paid use of the Kimi-K2.5-MXFP4. Support call Kimi-K2.5-MXFP4 model through api, including Node.js, Python, http.

Kimi-K2.5-MXFP4 huggingface.co Url

https://huggingface.co/amd/Kimi-K2.5-MXFP4

amd Kimi-K2.5-MXFP4 online free

Kimi-K2.5-MXFP4 huggingface.co is an online trial and call api platform, which integrates Kimi-K2.5-MXFP4's modeling effects, including api services, and provides a free online trial of Kimi-K2.5-MXFP4, you can try Kimi-K2.5-MXFP4 online for free by clicking the link below.

amd Kimi-K2.5-MXFP4 online free url in huggingface.co:

https://huggingface.co/amd/Kimi-K2.5-MXFP4

Kimi-K2.5-MXFP4 install

Kimi-K2.5-MXFP4 is an open source model from GitHub that offers a free installation service, and any user can find Kimi-K2.5-MXFP4 on GitHub to install. At the same time, huggingface.co provides the effect of Kimi-K2.5-MXFP4 install, users can directly use Kimi-K2.5-MXFP4 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Kimi-K2.5-MXFP4 install url in huggingface.co:

https://huggingface.co/amd/Kimi-K2.5-MXFP4

Url of Kimi-K2.5-MXFP4

Kimi-K2.5-MXFP4 huggingface.co Url

Provider of Kimi-K2.5-MXFP4 huggingface.co

amd
ORGANIZATIONS

Other API from amd

huggingface.co

Total runs: 179.1K
Run Growth: 87.8K
Growth Rate: 49.05%
Updated:April 14 2026
huggingface.co

Total runs: 117.5K
Run Growth: 12.1K
Growth Rate: 10.28%
Updated:July 17 2026
huggingface.co

Total runs: 105.8K
Run Growth: 16.2K
Growth Rate: 15.28%
Updated:June 19 2026
huggingface.co

Total runs: 25.8K
Run Growth: 12.3K
Growth Rate: 47.76%
Updated:July 27 2026
huggingface.co

Total runs: 12.3K
Run Growth: 5.9K
Growth Rate: 47.68%
Updated:October 09 2024
huggingface.co

Total runs: 11.2K
Run Growth: 1.3K
Growth Rate: 11.53%
Updated:August 12 2025
huggingface.co

Total runs: 2.5K
Run Growth: -533
Growth Rate: -19.83%
Updated:June 19 2026
huggingface.co

Total runs: 1.4K
Run Growth: -38.8K
Growth Rate: -2876.00%
Updated:June 19 2026
huggingface.co

Total runs: 948
Run Growth: -2.7K
Growth Rate: -290.47%
Updated:May 27 2026
huggingface.co

Total runs: 542
Run Growth: -4.8K
Growth Rate: -880.26%
Updated:June 19 2026
huggingface.co

Total runs: 517
Run Growth: -350
Growth Rate: -67.70%
Updated:November 15 2025