Alibaba

Qwen3.8 Flash-Next

180B

Parameters

111,4 Go

Q4_K_M file

≥ 112,9 Go

Recommended VRAM

262 144

Max context

Not measured yet

No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.

Measure my card →

Which cards should it fit on?

Cards on the site whose video memory covers the recommended 112,9 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published: 2026-08-24
Architecture: 48 layers · 2 KV heads · dimension 256
Attention: Hybrid: 12 of 48 layers use standard attention, the others a fixed-memory mechanism (Mamba, linear attention) — a very light cache.
Context cache (f16): ≈ 23 MB per 1,000 tokens · 0,8 Go for 32,768 tokens
GGUF file: bartowski/Qwen3.8-Flash-Next-GGUF · 4 files Download (111,4 Go)
Official repo: Qwen/Qwen3.8-Flash-Next

Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.