Kimi VL A3B Thinking 2506
Moonshot AI's Kimi VL A3B Thinking 2506.
Task Fit
Not marked for typed decisions in the current library.
Tool use, repo work, terminal workflows, and coding benchmarks.
Code generation, debugging, refactoring, and benchmark signal.
General writing, Q&A, and assistant use.
Document QA benefits from long context and instruction following.
Image or visual understanding, not necessarily image generation.
Not marked for image generation in the current library.
Not marked for video generation in the current library.
Not marked for voice in the current library.
Evidence level
How this is assessed →Memory and hardware-fit values are planning estimates unless a tested report is linked.
Variants and Quant Artifacts
Choose the artifact first; hardware fit follows from RAM, VRAM, format, and runtime.
| Quant | Format | Quality | Min RAM | Reco RAM | Runtime | Action |
|---|---|---|---|---|---|---|
| Q4_K_M | gguf | balanced | 4GB | 8GB | llama.cpp, lm-studio | Plan with this |
| Q5_K_M | gguf | balanced | 4GB | 8GB | llama.cpp, lm-studio | Plan with this |
| Q8_0 | gguf | high | 8GB | 12GB | llama.cpp, lm-studio | Plan with this |
| FP16 | safetensors | high | 12GB | 16GB | transformers, vllm | Plan with this |
Recommended Hardware
Lowest estimated 5-year cost that can run this model.
Enough unified/system memory with a balanced 5-year cost.
Highest local performance signal among compatible hardware.
Benchmarks
No benchmark data is available for this model yet.
Sources and compatibility
Execution evidence
Run Kimi VL A3B Thinking 2506 with a documented recipe
Recipes connect hardware, a model artifact, tools, settings, verification, and a reportable result.
No verified recipe is linked to this record yet.
Compatibility estimates remain available in the planner. A recipe appears here only after its exact stack and verification protocol are documented.
Similar Models
Moonshot AI's Kimi K2.7 Code.
Moonshot AI's Kimi K2.6.
Moonshot AI Kimi K3 is an open-weight 2.8T-parameter multimodal MoE model with 104B active parameters, native MXFP4 weights, always-on reasoning, tool use, and a 1M-token context window. The official release targets large multi-accelerator deployments through vLLM, SGLang, or TokenSpeed rather than consumer local hardware.