Qwen 3.5 9B (MLX 4-bit)

by Alibaba (Qwen)Chatunverified match

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context
32.8K tokens
Max output
8,192 tokens
Released
2026-03-05
Weights
Open

alibaba/qwen3-5-9b-mlx-4bit

Specifications

Full facts as recorded, incl. what is unknown.

Released
2026-03-05
Weights
Open
Input
Text, Image
Output
Text
Context window
32,768 max across endpoints
Max output
8,192
Providers
1
Epoch Capabilities Index
not evaluated
Direct price range
no comparable direct price
More details
Last updated
2026-04-04
Knowledge cutoff

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Cost calculator

Loading endpoints…

More from Alibaba (Qwen)

Newest Alibaba (Qwen) models in the catalogue. All Alibaba (Qwen) models

ModelReleasedContextListed price
Qwen Image 2.1 Pro2026-10-1665.5Kunpriced
Qwen 3.8 27B Fimi2026-10-05262K$0.10 via NanoGPT
Qwen 3.8 27B Kiwen2026-10-05262K$0.10 via NanoGPT
Qwen 3.8 27B Swift2026-10-05262K$0.10 via NanoGPT
Qwen 3.8 27B Kimiko2026-10-05262K$0.10 via NanoGPT
Qwen 3.8 27B Synthia2026-10-05262K$0.10 via NanoGPT
Qwen 3.8 27B Antislop2026-10-05262K$0.10 via NanoGPT
Qwen 3.8 27B DarkIdol2026-10-05262K$0.10 via NanoGPT
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model