Kimi K2.6 — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated September 6, 2026

Model library → Kimi K2.5 / K2.6 / K2.7 → Kimi K2.6

April 2026 successor to K2.5, same 1T-parameter MoE shape: 384 experts with 8 routed plus 1 shared, 61 layers, MLA attention, 256K context, Modified MIT. Adds video alongside image input through MoonViT. 80.2% on SWE-bench Verified and 66.7% on Terminal-Bench 2.0 — the strongest open-weight coder at release. Like K2.5 it needs ~605 GB resident at Q4_K_M: the 32B figure is active parameters per token, not what fits on your card.

Kimi K2.6 needs about 605 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters1 Trillion (32B active)
Context window256,000
ArchitectureMoE (384 experts, 8+1 shared, MLA) + MoonViT vision
ProviderMoonshot AI
LicenceModified MIT
Specified atQ4_K_M
System RAM768 GB
Record updated2026-09-06

Licence

Modified MIT — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

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.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K328.8 GB329.6 GB—Won't fit
Q3_K_M426.3 GB427.1 GB—Won't fit
Q4_K_M603.8 GB604.5 GB—Won't fit
Q5_K_M708.8 GB709.5 GB—Won't fit
Q6_K820.0 GB820.8 GB—Won't fit
Q8_01062.5 GB1063.3 GB—Won't fit
F162000.0 GB2000.8 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Kimi K2.6 VRAM calculator.

Deploy in the Cloud NowRunPod

or compare on Vast.ai

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.

How to Run Kimi K2.6

Install Ollama, then run:

ollama run hf.co/moonshotai/Kimi-K2.6-Instruct-Q4_K_M

Weights on Hugging Face: moonshotai/Kimi-K2.6-Instruct.

Published Benchmark Scores

Quality scores as published by the model's authors or an independent evaluator — not throughput, and not measured by us.

BenchmarkScoreProvenance
SWE-bench Verified80.2 / 100 %reported · https://benchlm.ai/models/kimi-2-6
Terminal-Bench 2.066.7 / 100 %reported · https://benchlm.ai/models/kimi-2-6

Best for: coding, agentic, multimodal, research, complex tasks.

Other Kimi K2.5 / K2.6 / K2.7 Sizes

Kimi K2.6 — Frequently Asked Questions

How much VRAM does Kimi K2.6 need?
About 605 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Kimi K2.6 run on an RTX 4090 (24 GB)?
No. Kimi K2.6 needs about 605 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Kimi K2.6 locally?
Install Ollama and run `ollama run hf.co/moonshotai/Kimi-K2.6-Instruct-Q4_K_M`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Kimi K2.5 / K2.6 / K2.7 come in?
Kimi K2.5 (605 GB), Kimi K2.6 (605 GB), Kimi K2.5 1T (32B Active) (605 GB), Kimi K2.7 Code (605 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Kimi K2.5 / K2.6 / K2.7 models | VRAM calculator | Check your own hardware