Qwen3.5

Qwen3.5-9B

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

Parameters (B)	9.653
Architecture	dense
Layers / KV heads / head dim	32 / 4 / 256
Context window	262144
Modalities	in: text, image; out: text
GGUF	available
Commercial use	yes

Minimum hardware (estimate)

At Q4_K_M and 8k context, total working set ≈ 7.5 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

Benchmark	Value	Uncertainty	Run by	Source
Terminal-Bench	9.2%	±0.0240	third-party	epoch-ai

Provenance

identity, license, architecture, parameter count: https://huggingface.co/Qwen/Qwen3.5-9B (retrieved 2026-08-10)

HF: Qwen/Qwen3.5-9B · snapshot 2026-08-10