[models]By ByteBulletin Editor
Escha Labs ships 2-bit Qwen3.6-35B-A3B build that runs on a 24GB GPU
A 12.3GB MoE quant packs a 35B model onto consumer cards, with quality within noise of FP8 on most benchmarks.
[tag]
#qwen
2 stories
[tag]
2 stories
A 12.3GB MoE quant packs a 35B model onto consumer cards, with quality within noise of FP8 on most benchmarks.
Alibaba releases its largest open-weight model yet, Qwen3.8-Max, claiming it rivals Anthropic’s Claude Fable 5, with weights due next week.
