Skip to content
Weights Not Walls
Menu

moonshotai

Kimi-K2.6

Reviewedaccepts images
Size
1.0T parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: unsloth/Kimi-K2.6-GGUF
Licence
unknown, MiniMax Model LicenseOur reading, check the licence: Despite the id, this text is the MiniMax Model License (dated for MiniMax-M2.5), not a modified MIT licence: it lets you use, copy, change and distribute the model with no limit on commercial use and no user or revenue threshold. If you distribute the model or a product or service that uses it, you must include the licence, mark changed files and keep a Notice file, though you may license your own changes differently. A Prohibited Uses Policy is part of the licence and bars, among other things, any military purpose and fully automated decisions that adversely affect someone's legal rights.
On the Hub since
14 Apr 2026the date the repo was created
Context length
256k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)KimiK25ForConditionalGeneration
On Hugging Face
moonshotai/Kimi-K2.6199k downloads in the last 30 days, 1.6k likes

Scores

23 independent results on 21 eval sets
Chess PuzzlesRe-run by Epoch AI
  • default setting20.0%±4.013 Oct 2026, log

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5-2_max, 79.0% (Anthropic). All 166 results

EBR-benchRe-run by Epoch AI
  • default setting2.4%25 Jun 2026, Epoch AI

Epoch's name: kimi-k2.6. Best closed model on this set: gpt-6.2-astra_max, 92.4% (OpenAI). All 33 results

  • default setting39.0%±2.97 May 2026, Epoch AI

Epoch's name: kimi-k2.6. Best closed model on this set: gpt-5.5-pro-pre-release_high, 52.4% (OpenAI). All 101 results

  • default setting14.6%±5.18 May 2026, Epoch AI

Epoch's name: kimi-k2.6. Best closed model on this set: gdm-ai-co-mathematician, 47.9% (Google DeepMind). All 72 results

  • default setting25.6%±7.110 Jun 2026, log

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5-2_max, 100.0% (Anthropic). All 83 results

  • default setting57.2%±2.910 Jun 2026, log

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5-2_max, 95.1% (Anthropic). All 127 results

Furniture AssemblyRe-run by Epoch AI
  • default setting21.7%±5.211 Sep 2026, Epoch AI

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5-2_max, 90.0% (Anthropic). All 41 results

GPQA diamondRe-run by Epoch AI
  • default setting90.8%±1.71 May 2026, log

Epoch's name: kimi-k2.6. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results

Mystery Game PuzzlesRe-run by Epoch AI
  • default setting18.0%±3.917 Jul 2026, Epoch AI
  • effort none12.0%±3.329 Aug 2026, log

Epoch's name: kimi-k2.6. Best closed model on this set: gpt-6.2-astra_max, 95.0% (OpenAI). All 148 results

OTIS Mock AIME 2024-2025Re-run by Epoch AI
  • default setting96.1%±2.42 May 2026, log

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results

SimpleQA VerifiedRe-run by Epoch AI
  • default setting34.9%±1.510 Aug 2026, Epoch AI

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5-2_max, 94.0% (Anthropic). All 105 results

SWE-Bench verifiedRe-run by Epoch AI
  • default setting76.7%±1.98 May 2026, log

Epoch's name: kimi-k2.6. Best closed model on this set: claude-opus-4-7_max, 83.5% (Anthropic). All 35 results

Epoch's name: kimi-k2.6. Best closed model on this set: gemini-4-carbon_unknown, 58.6% (Google DeepMind). All 38 results

CritPtReported

Epoch's name: kimi-k2.6. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results

DTBenchReported

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results

ExploitBenchReported

Epoch's name: kimi-k2.6. Best closed model on this set: claude-mythos-preview-early, 73.8% (Anthropic). All 20 results

GBAEvalReported

Epoch's name: kimi-k2.6. Best closed model on this set: claude-opus-5-5_unknown, 90.6% (Anthropic). All 28 results

LMCAReported

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results

OSWorld 2.0Reported

Epoch's name: kimi-k2.6. Best closed model on this set: claude-opus-5_max, 31.4% (Anthropic). All 16 results

ProofBenchReported

Epoch's name: kimi-k2.6. Best closed model on this set: claude-fable-5-1_max, 100.0% (Anthropic). All 85 results

WeirdMLReported

Epoch's name: kimi-k2.6. Best closed model on this set: gpt-6-astra_promax, 93.6% (OpenAI). All 173 results

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.54 GB, worked out from the model's config (moonshotai/Kimi-K2.6), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

unsloth/Kimi-K2.6-GGUF (converted by unsloth), 4.2k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-F16.gguf (0.89 GB), not counted below.

FormatSizeMemory neededGet it
UD-Q2_K_XL317.1 GBfile size, 8 parts318.1 GB317.1 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2.6-GGUF:UD-Q2_K_XL
Download
hf download unsloth/Kimi-K2.6-GGUF --include "UD-Q2_K_XL/Kimi-K2.6-UD-Q2_K_XL-*-of-00008.gguf" --local-dir Kimi-K2.6-GGUF
UD-Q4_K_XL543.6 GBfile size, 14 parts544.7 GB543.6 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2.6-GGUF:UD-Q4_K_XL
Download
hf download unsloth/Kimi-K2.6-GGUF --include "UD-Q4_K_XL/Kimi-K2.6-UD-Q4_K_XL-*-of-00014.gguf" --local-dir Kimi-K2.6-GGUF
UD-Q8_K_XL553.7 GBfile size, 14 parts554.7 GB553.7 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2.6-GGUF:UD-Q8_K_XL
Download
hf download unsloth/Kimi-K2.6-GGUF --include "UD-Q8_K_XL/Kimi-K2.6-UD-Q8_K_XL-*-of-00014.gguf" --local-dir Kimi-K2.6-GGUF
BF161912.2 GBfile size, 46 parts1913.2 GB1912.2 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2.6-GGUF:BF16
Download
hf download unsloth/Kimi-K2.6-GGUF --include "BF16/Kimi-K2.6-BF16-*-of-00046.gguf" --local-dir Kimi-K2.6-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 6bitspicyneuron/Kimi-K2.6-MLX-3.6bit427.6 GBfile size428.6 GB427.6 + 0.54 + 0.50Download page
MLXmlx-community/Kimi-K2.6-mlx-DQ3_K_M-q8438.3 GBfile size439.3 GB438.3 + 0.54 + 0.50Download page

Original weights

The maker's own weights are packed into integer tensors, so the safetensors header gives no size we can trust; the repo lists the real file sizes.

hf download moonshotai/Kimi-K2.6 --local-dir Kimi-K2.6
Other conversions (10; sizes not read)

The Hub tags 45 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

12 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
DigitalOcean$0.57$2.40256knot given480.9 s100.0%yesyes
Inceptron$0.58$2.87256kint4780.5 s100.0%yesyes
Novita$0.80$3.40256knot given314.0 s97.4%yesyes
SiliconFlow$0.77$3.40256kfp8210.9 s100.0%yesyes
CoreWeave$0.65$3.41256kfp41130.8 s99.8%yesyes
Crusoe$0.70$3.50256kbf16700.4 s99.3%yesyes
DeepInfra$0.75$3.50256kfp4200.8 s98.6%yesyes
Parasail$0.75$3.50256kint4750.6 s99.9%yesyes
Venice$0.75$3.50250kint4240.7 s89.4%yesyes
Cloudflare$0.95$4.00256knot given530.9 s100.0%yesyes
Moonshot AIthe maker$0.95$4.00256knot given301.3 s99.5%yesyes
featherless-ai???not given???not givennot given

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "moonshotai/Kimi-K2.6:digitalocean", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.