Model datasheet · Qwen3.5

Qwen3.5 9B

The most-downloaded local model of 2026 (12M+/month): vision, 256K context, and vendor claims that beat gpt-oss-20b from 9B dense. Sparse independent data so far — most cells honestly unrated.

Vendor: Alibaba
Architecture: Dense · 9B
Context: 262,144 tokens
License: Apache-2.0
Released: 2026-03-02
Vision: Yes

→ GGUF (llama.cpp / LM Studio / Ollama) → MLX (Apple Silicon)

§1 Characteristics by quantization band

Q2–Q3 — 2–3 bit

4.5GB weights · e.g. Q3_K_M + KV: 256MB at 8K · 1GB at 32K · 4GB at 128K

— Not yet rated · contributions welcome —

Q4–Q5 — 4–5 bit

5.5GB weights · e.g. Q4_K_M , mlx-4bit + KV: 256MB at 8K · 1GB at 32K · 4GB at 128K

— Not yet rated · contributions welcome —

Q6–Q8 — 6–8 bit

7.5GB weights · e.g. Q6_K , Q8_0 + KV: 256MB at 8K · 1GB at 32K · 4GB at 128K

— Not yet rated · contributions welcome —

FP16 — full precision (fp16/bf16)

18GB weights · e.g. bf16 + KV: 256MB at 8K · 1GB at 32K · 4GB at 128K

Math & reasoning

8/10

data checked Aug 2026

vendor-model-card — GPQA Diamond = 81.7 @ bf16 · vendor-reported · 2026-08-30
MMLU-Pro: 82.5 — vendor-reported; absent from Vectara HHEM and Aider as of 2026-08-30, so everything else is unrated.

§2 Known issues & what fixes them

— No documented issues yet · which means unreviewed, not flawless —