Qwen3.5 9B locally: the model 'ollama run qwen3.5' actually gives you

Type ollama run qwen3.5 and this is the model you get — the 9B. What it is, how little VRAM it needs, and the cheapest card that runs it well.

Aliteq
Lena Fischer · AI & Local Compute Editor

The short answer

Qwen3.5 9B is the model you get when you type ollama run qwen3.5 — it's the default tag. A 9B dense model with a 256K context, it needs about 6.7 GB at Q4_K_M (computed by our VRAM engine), so it…

9B params, dense, 256K context (extensible), Apache-2.0 — from the model card.

The bare ollama run qwen3.5 pulls this 9B (verified on ollama.com/library).

Q4_K_M ~6.7 GB, Q8_0 ~10.8 GB (computed by our VRAM engine, 16K context).

Aliteq

Read the full story

Qwen3.5 9B locally: the model 'ollama run qwen3.5' actually gives you

Read the full story on Aliteq