Qwen3.6

Qwen3.6-35B-A3B

Alibaba (Qwen team) · open-permissive apache-2.0

Parameters (B)35.952
Architecturemoe
Layers / KV heads / head dim40 / 2 / 256
Context window262144
Modalitiesin: text, image; out: text
GGUFavailable
Commercial useyes

Minimum hardware (estimate)

At Q4_K_M and 8k context, total working set ≈ 23.0 GiB. On a machine with 64 GiB system RAM and no discrete GPU: CPU-only, slow. Limiting factor: No GPU VRAM; fits in system RAM but inference will be CPU-bound.

Open in fit advisor

Scores

BenchmarkValueUncertaintyRun bySource
GPQA Diamond84.9%±0.0255third-partyepoch-ai
OTIS Mock AIME 2024-202586.7%±0.0512third-partyepoch-ai
Terminal-Bench24.6%±0.0320third-partyepoch-ai

Provenance

HF: Qwen/Qwen3.6-35B-A3B · snapshot 2026-08-10