skip to content
gigarouter gigarouter
models / vision-language · coming soon

Qwen 3.6 27B

Qwen/Qwen3.6-27B-FP8

published Apr 2026 · updated Apr 2026

Qwen 3.6 27B is a vision-language model (VLM) optimized for agentic coding and repository-level reasoning, with FP8 quantization for efficient deployment.

est. price
~$1.341
/ 1k images · estimated, set at launch
API providers
0
downloads / mo
4.9M
license
apache-2.0

specs

TaskVision-Language (Image to Text)
ArchitectureCausal Language Model with Vision Encoder
Parameters27B
Context Length262,144 tokens (extensible to ~1M)

about this model

Qwen3.6-27B-FP8 is a vision-language model (VLM) that combines a causal language model with a vision encoder, optimized for agentic coding and repository-level reasoning. Gigarouter hosts this FP8-quantized variant (block size 128, performance nearly identical to the original) as an OpenAI-compatible API, supporting native context lengths of 262,144 tokens, extendable to 1,010,000 tokens. Qwen3.6 logo

Key Strengths

The model excels at frontend workflows and multi-step agentic tasks. A new "thinking preservation" feature retains reasoning context from historical messages, reducing overhead in iterative development. Fine-grained FP8 quantization ensures low memory usage without measurable accuracy loss.

Benchmark Results (Coding Agent)

The table below highlights performance on major software engineering benchmarks. Full comparisons with Qwen3.5-27B, Qwen3.5-397B-A17B, Gemma4-31B, Claude 4.5 Opus, and Qwen3.6-35B-A3B appear in the image.

BenchmarkQwen3.6-27B
SWE-bench Verified77.2
SWE-bench Pro53.5
SWE-bench Multilingual71.3
Terminal-Bench 2.059.3
SkillsBench (Avg5)48.2
NL2Repo36.2
Claw-Eval (Avg)72.4
QwenClawBench53.4
Full benchmark comparison across models

For additional details, see the Qwen3.6-27B blog post.

best for

FAQ

What is Qwen 3.6 27B best for?

It excels at agentic coding, repository-level reasoning, and frontend workflows, with strong results on SWE-bench, Terminal-Bench, and Claw-Eval.

How does it compare to Qwen 3.5 27B?

Qwen 3.6 27B shows improvements across coding benchmarks: SWE-bench Verified 77.2 vs 75.0, Terminal-Bench 2.0 59.3 vs 41.6, and Claw-Eval Pass^3 60.6 vs 46.2.

What context length does it support?

Native context length is 262,144 tokens, extensible up to approximately 1,010,000 tokens.

How can I call this model via API?

Use the gigarouter OpenAI-compatible endpoint with your API key to send text and image inputs.

Is this model quantized?

Yes, it uses fine-grained FP8 quantization with a block size of 128, maintaining near-lossless performance compared to the original model.

not yet live

We're benchmarking and onboarding Qwen 3.6 27B as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related vision-language models

compare all →