Qwen3.8-27B-AutoRound-W4A16-v2

Model Details

This is a W4A16 quantization of Qwen/Qwen3.8-27B, generated by AutoRound. Please follow the license of the original model.

Quantization Details

Evaluation

Benchmark Score
gsm8k 0.9697
hellaswag 0.8241
mmlu 0.8269
piqa 0.8107

Produced with autoquant-agent — agent-driven quantize + evaluate + self-heal.

Downloads last month
-
Safetensors
Model size
6B params
Tensor type
I32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for LeaderboardModel1/Qwen3.8-27B-AutoRound-W4A16-v2

Base model

Qwen/Qwen3.8-27B
Quantized
(847)
this model