Written by Jakub Rusinowski · Last updated August 15, 2026
Model library → Kimi K2.5 / K2.6 / K2.7 → Kimi K2.7 Code
Moonshot's coding-specialised build, layered directly on top of K2.6: 1 trillion total parameters with 32B active per token across 384 experts (8 selected plus 1 shared), 61 layers, MLA attention, and a 400M-parameter MoonViT encoder for image and video input. Reported ~30% fewer reasoning tokens than K2.6 at higher coding scores. Weights ship in native INT4 via quantization-aware training. 256K context. At ~340 GB even in INT4 this is a datacenter deployment, not a desktop one — most people reach it through the API.
Kimi K2.7 Code needs about 605 GB of VRAM at INT4 (native) — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 1 Trillion (32B active) |
| Context window | 262,144 |
| Architecture | MoE (384 experts, MLA) + MoonViT vision |
| Provider | Moonshot AI |
| Licence | Modified MIT (attribution above ~100M MAU / ~$20M monthly revenue) |
| Specified at | INT4 (native) |
| System RAM | 768 GB |
| Record updated | 2026-08-15 |
Modified MIT — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 328.8 GB | 329.6 GB | — | Won't fit |
| Q3_K_M | 426.3 GB | 427.1 GB | — | Won't fit |
| Q4_K_M | 603.8 GB | 604.5 GB | — | Won't fit |
| Q5_K_M | 708.8 GB | 709.5 GB | — | Won't fit |
| Q6_K | 820.0 GB | 820.8 GB | — | Won't fit |
| Q8_0 | 1062.5 GB | 1063.3 GB | — | Won't fit |
| F16 | 2000.0 GB | 2000.8 GB | — | Won't fit |
Want the memory numbers alone, at every quantization level and your own context length? Use the Kimi K2.7 Code VRAM calculator.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Install Ollama, then run:
ollama run kimi-k2
Weights on Hugging Face: moonshotai/Kimi-K2.7-Code.
Best for: agentic coding, software engineering, repo level, multimodal, cloud api.
← All Kimi K2.5 / K2.6 / K2.7 models | VRAM calculator | Check your own hardware