Skip to content
Weights Not Walls
Menu

moonshotai

Kimi-K3.1-Pro

Reviewedaccepts images
Size
2.8T parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: KarLexAI/Kimi-K3.1-Pro-GGUF
Licence
unknown, Kimi K3.1-Pro LicenseOur reading, check the licence: Commercial use is allowed, but if you or an affiliate run a Model as a Service business and your combined revenue exceeds 20 million US dollars over any consecutive 12 months, you need a separate agreement with Moonshot AI before commercial use. Products or services with more than 100 million monthly active users or more than 20 million US dollars in monthly revenue must prominently display "Kimi K3.1-Pro" in their user interface. Neither rule applies to internal use or to use through Moonshot AI's official products or certified inference partners; otherwise it is MIT style, with no duty to share changes.
On the Hub since
2 Nov 2026the date the repo was created
Context length
1M tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)KimiK31ForConditionalGeneration
On Hugging Face
moonshotai/Kimi-K3.1-Pro61k downloads in the last 30 days, 2.3k likes

Scores

15 independent results on 15 eval sets
Chess PuzzlesRe-run by Epoch AI
  • effort max45.0%±5.06 Nov 2026, log

Epoch's name: kimi-k3.1-pro-together. Best closed model on this set: claude-fable-5-2_max, 79.0% (Anthropic). All 166 results

  • effort max65.9%±7.56 Nov 2026, Epoch AI

Epoch's name: kimi-k3.1-pro-together. Best closed model on this set: claude-fable-5-2_max, 100.0% (Anthropic). All 83 results

  • effort max78.2%±2.46 Nov 2026, Epoch AI

Epoch's name: kimi-k3.1-pro-together. Best closed model on this set: claude-fable-5-2_max, 95.1% (Anthropic). All 127 results

Furniture AssemblyRe-run by Epoch AI
  • effort max55.8%±6.46 Nov 2026, Epoch AI

Epoch's name: kimi-k3.1-pro-together. Best closed model on this set: claude-fable-5-2_max, 90.0% (Anthropic). All 41 results

GPQA diamondRe-run by Epoch AI
  • effort max94.2%±1.46 Nov 2026, log

Epoch's name: kimi-k3.1-pro-together. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results

Mystery Game PuzzlesRe-run by Epoch AI
  • effort max42.0%±5.06 Nov 2026, Epoch AI

Epoch's name: kimi-k3.1-pro-together. 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
  • effort max100.0%6 Nov 2026, log

Epoch's name: kimi-k3.1-pro-together. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results

SimpleQA VerifiedRe-run by Epoch AI
  • effort max62.2%±1.56 Nov 2026, log

Epoch's name: kimi-k3.1-pro-together. Best closed model on this set: claude-fable-5-2_max, 94.0% (Anthropic). All 105 results

APEX-AgentsReported

Epoch's name: kimi-k3.1-pro. Best closed model on this set: gemini-4-carbon_unknown, 84.2% (Google DeepMind). All 66 results

CritPtReported

Epoch's name: kimi-k3.1-pro. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results

DTBenchReported

Epoch's name: kimi-k3.1-pro. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results

GDP.pdfReported

Epoch's name: kimi-k3.1-pro. Best closed model on this set: gemini-4-carbon_high, 56.4% (Google DeepMind). All 19 results

LMCAReported

Epoch's name: kimi-k3.1-pro. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results

ProofBenchReported

Epoch's name: kimi-k3.1-pro. Best closed model on this set: claude-fable-5-1_max, 100.0% (Anthropic). All 85 results

WeirdML v3Reported

Epoch's name: kimi-k3.1-pro. Best closed model on this set: claude-fable-5-2_xhigh, 65.3% (Anthropic). All 27 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: 0.82 GB, worked out from the model's config (moonshotai/Kimi-K3.1-Pro), 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

KarLexAI/Kimi-K3.1-Pro-GGUF (converted by KarLexAI), 9.9k 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 (0.84 GB), not counted below.

FormatSizeMemory neededGet it
IQ1_S552.0 GBfile size, 14 parts553.3 GB552.0 + 0.82 + 0.50
Commands
llama.cpp
llama-server -hf KarLexAI/Kimi-K3.1-Pro-GGUF:IQ1_S
Download
hf download KarLexAI/Kimi-K3.1-Pro-GGUF --include "KLX-IQ1_S/Kimi-K3.1-Pro-KLX-IQ1_S-*-of-00014.gguf" --local-dir Kimi-K3.1-Pro-GGUF
IQ1_M603.4 GBfile size, 15 parts604.7 GB603.4 + 0.82 + 0.50
Commands
llama.cpp
llama-server -hf KarLexAI/Kimi-K3.1-Pro-GGUF:IQ1_M
Download
hf download KarLexAI/Kimi-K3.1-Pro-GGUF --include "KLX-IQ1_M/Kimi-K3.1-Pro-KLX-IQ1_M-*-of-00015.gguf" --local-dir Kimi-K3.1-Pro-GGUF
IQ2_XXS661.1 GBfile size, 17 parts662.4 GB661.1 + 0.82 + 0.50
Commands
llama.cpp
llama-server -hf KarLexAI/Kimi-K3.1-Pro-GGUF:IQ2_XXS
Download
hf download KarLexAI/Kimi-K3.1-Pro-GGUF --include "KLX-IQ2_XXS/Kimi-K3.1-Pro-KLX-IQ2_XXS-*-of-00017.gguf" --local-dir Kimi-K3.1-Pro-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX mxfp4pipenetwork/Kimi-K3.1-Pro-REAP80-code-MLX-mxfp4-q4299.8 GBfile size301.1 GB299.8 + 0.82 + 0.50Download page
MLXinferencerlabs/Kimi-K3.1-Pro-MLXse1454.0 GBfile size1455.3 GB1454.0 + 0.82 + 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-K3.1-Pro --local-dir Kimi-K3.1-Pro
Other conversions (10; sizes not read)

The Hub tags 23 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

19 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
Decart$1.20$6.001Mmxfp4413.2 s100.0%yesyes
Relace$0.24$8.401Mfp4661.5 s100.0%yesno
Wafer$0.25$8.801Mmxfp4920.6 s100.0%yesyes
InferenceNet$1.80$9.001Mmxfp41020.6 s100.0%yesyes
Sail Research$1.04$9.351Mfp4390.7 s100.0%yesyes
Makora$2.00$9.491Mnot given761.1 s97.3%yesyes
DeepInfra$1.90$9.501Mbf16410.9 s99.7%yesyes
AkashML$1.75$101Mfp4741.5 s99.8%yesyes
DigitalOcean$2.00$101Mnot given951.5 s100.0%yesyes
Fireworks$2.00$101Mnot given404.0 s97.5%yesyes
Modal$2.00$101Mmxfp4820.8 s100.0%yesyes
Moonshot AIthe maker$2.00$101Mmxfp4313.1 s99.9%yesyes
Nebius$2.00$101Mfp41640.8 s100.0%yesyes
Parasail$2.00$101Mfp4931.0 s99.9%yesyes
PrimaLabs$2.00$101Mmxfp4851.1 s99.8%yesyes
River$2.00$101Mnot given960.7 s99.9%yesyes
Together$2.00$101Mnot given401.6 s99.3%yesyes
Morph$1.05$15.71Mfp8432.2 s99.1%yesyes
Amazon Bedrock$4.00$201Mnot given1171.7 s98.2%yesno

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-K3.1-Pro:decart", "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.