Hugging Face's logo

RedHatAI
/
Kimi-K2-Instruct-quantized.w4a16

Text Generation
Safetensors
vllm
deepseek_v3
neuralmagic
redhat
llmcompressor
quantized
INT4
GPTQ
conversational
custom_code
compressed-tensors
Model card Files
xet
Community
3

Preliminary version of the model

Evaluations

  • GSM8k, 5-shot via lm-evaluation-harness
moonshotai/Kimi-K2-Instruct                            = 94.92
RedHatAI/Kimi-K2-Instruct-quantized.w4a16 (this model) = 94.84

More evals coming very soon...

Downloads last month
4,377
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for RedHatAI/Kimi-K2-Instruct-quantized.w4a16

Base model

moonshotai/Kimi-K2-Instruct
Quantized
(11)
this model