qwen
9B parameters
Commercial OK
Multimodal
Reviewed July 2026

Qwen3.5 9B

Qwen3.5 9B is Alibaba's dense 9B release from March 2026 under Apache-2.0. It takes text and image input, runs a 256K context, and covers 201 languages. The qwen3.5 family is at 15.7M Ollama pulls (#14 in the library); the Q4_K_M build is 6.6GB.

License: Apache-2.0·Released Mar 2, 2026·Context: 262,144 tokens

Overview

Qwen3.5 9B is Alibaba's dense 9B release from March 2026 under Apache-2.0. It takes text and image input, runs a 256K context, and covers 201 languages. The qwen3.5 family is at 15.7M Ollama pulls (#14 in the library); the Q4_K_M build is 6.6GB.

Strengths

  • 201-language coverage in a 9B footprint
  • Apache-2.0 license with commercial use allowed
  • 6.6GB Q4_K_M leaves KV-cache headroom on 12GB cards

Weaknesses

  • Image input only on the multimodal side — no audio
  • 9B quality ceiling on hard reasoning versus 12-20B peers
  • Filling the 256K window needs far more VRAM than the weights suggest
BLK · QUALITY BENCHMARKreviewed · raw logs

Reviewed quality benchmarks

First-party rows were run by RunLocalAI; reviewed community rows are labeled in the data. Every row links to the raw test-run log.

BenchmarkQuantRuntime / HardwareScoreRaw log
HumanEval+
tested 2026-07-19
Q4_K_M
ollama-0.32
rtx-3080-16gb-mobile
42.7/100
Gist →

Q4_K_M note:First-party HumanEval+ on RTX 3080 Laptop 16GB via Ollama 0.32. Windows-safe scoring via scripts/evalplus_score_windows.py. July 2026 campaign.

Want to verify? Every row links to its Gist with full stdout and stderr of the run. The runner script is in the public repo (scripts/run-humaneval-plus.ts) — reproducible end-to-end. Browse all coding scores at /benchmarks/coding.

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M6.6 GB8 GB

Get the model

Ollama

One-line install

ollama run qwen3.5:9bRead our Ollama review →

Hardware that runs this

Cards with enough VRAM for at least one quantization of Qwen3.5 9B.

NVIDIA GB200 NVL72
13824GB · nvidia
AMD Instinct MI350X
288GB · amd
NVIDIA B300 (Blackwell Ultra)
288GB · nvidia
AMD Instinct MI355X
288GB · amd
AMD Instinct MI325X
256GB · amd
AMD Instinct MI300X
192GB · amd
NVIDIA B200
192GB · nvidia
NVIDIA H100 NVL
188GB · nvidia
Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Step up
More capable — bigger memory footprint
Step down
Smaller — faster, runs on weaker hardware

Frequently asked

What's the minimum VRAM to run Qwen3.5 9B?

8GB of VRAM is enough to run Qwen3.5 9B at the Q4_K_M quantization (file size 6.6 GB). Higher-quality quantizations need more.

Can I use Qwen3.5 9B commercially?

Yes — Qwen3.5 9B ships under the Apache-2.0, which permits commercial use. Always read the license text before deployment.

What's the context length of Qwen3.5 9B?

Qwen3.5 9B supports a context window of 262,144 tokens (about 262K).

How do I install Qwen3.5 9B with Ollama?

Run `ollama pull qwen3.5:9b` to download, then `ollama run qwen3.5:9b` to start a chat session. The default quantization is Q4_K_M.

Does Qwen3.5 9B support images?

Yes — Qwen3.5 9B is multimodal and accepts text + vision inputs. Vision support requires a runner that handles its image-conditioning architecture.

Source: Vendor official documentation

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Compare hardware
Buyer guides
When it doesn't work
Recommended hardware
Before you buy

Verify Qwen3.5 9B runs on your specific hardware before committing money.

Will it run on my hardware? →Custom hardware comparison →GPU recommender (4 questions) →