Downloads · 30 days
226
23% of all-time downloads
d-alistarh/Qwen3.6-27B-GSQ-Q3_K_M-GGUF
Qwen3.6-27B-GSQ-Q3_K_M-GGUF is a machine learning model from d-alistarh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Quantized with GSQ (Gumbel-Softmax Quantization). MLP and full-attention projections use GSQ-optimized weights; GatedDeltaNet SSM projections use standard quantization.
Downloads · 30 days
226
23% of all-time downloads
All-time downloads
966
Public
Repo size
13.6 GB
Likes
4
Public
Click a slice to open those files.
.gguf13.6 GB · 100%
From the Hugging Face model README
Quantized with GSQ (Gumbel-Softmax Quantization). MLP and full-attention projections use GSQ-optimized weights; GatedDeltaNet SSM projections use standard quantization.
| Model | PPL | Delta vs Std |
|---|---|---|
| Standard Q3_K_M (bartowski) | 7.19 | — |
| Unsloth Dynamic Q3_K_M | 7.19 | +0.00 |
| GSQ (this model) | 7.15 | -0.04 (-0.6%) |