Model Detail human-review-recommended

Qwen3 235B-A22B

Alibaba's flagship Qwen3. Competitive with GPT-4 class models.

AlibabaQWEN3apache-2.02025-07
Parameters
235B
22B active
Context window
131K
Long context
Architecture
decoder only transformer
moe
Quality score
92
Planner signal

Task Fit

Code AgentSupported

Tool use, repo work, terminal workflows, and coding benchmarks.

CodeSupported

Code generation, debugging, refactoring, and benchmark signal.

ChatSupported

General writing, Q&A, and assistant use.

RAGSupported

Document QA benefits from long context and instruction following.

VisionNot a fit

Not marked for vision in the current library.

Image GenerationNot a fit

Not marked for image generation in the current library.

Video GenerationNot a fit

Not marked for video generation in the current library.

VoiceNot a fit

Not marked for voice in the current library.

Source Confidence

Overallhigh · 94/100
ParametersReviewed / seeded
Task fitReviewed / seeded
MemorySeeded artifact
LicenseSource / seed
BenchmarksAvailable
Hardware fitCalculated

Variants and Quant Artifacts

Choose the artifact first; hardware fit follows from RAM, VRAM, format, and runtime.

3 artifacts
QuantFormatQualityMin RAMReco RAMRuntimeAction
Q2_Kggufcompact128GB192GBollama, llama.cpp, lm-studio Plan with this
Q3_K_Mggufcompact128GB192GBollama, llama.cpp, lm-studio Plan with this
Q4_K_Mggufbalanced145GB192GBollama, llama.cpp, lm-studio Plan with this

Benchmarks

Gsm8k92%
Humaneval85%
MMLU84%

Source and Review

Hugging FaceQwen/Qwen3-235B-A22B-Instruct-2507
Ollamaqwen3:235b
Verificationhuman-review-recommended
Artifact sourceseeded
Default variantQwen3 235B-A22B Coder
Tool callingSupported

Similar Models

Continue planning your local AI setup