Consider it when…
- Evaluate screenshots, diagrams or mixed text-image instructions
- Prototype coding assistance with visual context
- Test multimodal agent workflows on a controlled local system
Qwen/Qwen3.5-9BA nine-billion-parameter Qwen vision-language model for visual understanding, coding and agent-oriented local evaluation.
A current mid-sized Qwen model with a large native context limit.
The pinned Qwen model card documents a vision encoder, native 262,144-token context and image-text-to-text use.
Qwen/Qwen3.5-9Bc20223623576These are Maviter calculations at an 8,192-token context—not publisher hardware requirements or proof that a runtime supports this release.
Parameters × 4 bits, converted to GiB.
Runtime reserve and formula-backed KV cache.
Calculated working set rounded upward.
A planning band with headroom—not a guarantee.
Run the exact publisher release, on the intended runtime, with inputs from the work it must actually perform.
c202236235762e1c871ad0ccb60c8ee5ba337b9aOpen source ↗Pinned model cardCapabilities, licence and usage notesREADME.md at the recorded revisionRead card ↗The evidence ledger pins an exact publisher revision and monitors it for drift. A source check does not independently reproduce benchmarks or certify production suitability.
The publisher provides discoverable weights, but runtime support and performance are machine-specific. Use Maviter's fit calculator, then run one controlled test.
This record documents downloadable weights. It does not assert a provider-hosted API ID, current price, rate limit or data policy.
No. The pinned links return to the publisher. Maviter does not mirror binaries or endorse unaudited third-party quantisations.