login sign up

Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses - Quesma Blog

quesma.com · first added by @hacker
saved by
2 people
discussions · 4
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses 286 pts · 139 comments · Sep 2026 286 pts · 139 comments · Sep 2026
0 people saved or upvoted this
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses 15 pts · 2 comments · Aug 2026 15 pts · 2 comments · Aug 2026
0 people saved or upvoted this
see all 4 →
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses 3 pts · 2 comments · Aug 2026 3 pts · 2 comments · Aug 2026
0 people saved or upvoted this
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses 3 pts · 1 comment · Sep 2026 3 pts · 1 comment · Sep 2026
0 people saved or upvoted this
from the discussion · 5
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF · Hugging Face huggingface.co huggingface.co
0 people saved or upvoted this
Why Gated DeltaNet Survives 4-Bit Quantization:NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM arxiv.org arxiv.org
0 people saved or upvoted this
prism-ml/Bonsai-27B-mlx-1bit · Hugging Face huggingface.co huggingface.co
0 people saved or upvoted this
Jackrong/Qwopus3.8-27B-Flash-GGUF · Hugging Face huggingface.co huggingface.co
0 people saved or upvoted this
Qwen/Qwen3.8-27B · Hugging Face huggingface.co huggingface.co
0 people saved or upvoted this