Skip to content
Weights Not Walls
Menu

moonshotai

Kimi-K2-Thinking

Reviewed
Size
1.0T parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: unsloth/Kimi-K2-Thinking-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
4 Nov 2025the date the repo was created
Context length
256k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)DeepseekV3ForCausalLM
On Hugging Face
moonshotai/Kimi-K2-Thinking59k downloads in the last 30 days, 1.7k likes

Scores

9 independent results on 7 eval sets
  • default setting21.4%±2.45 Dec 2025, log

Epoch's name: moonshotai/Kimi-K2-Thinking. Best closed model on this set: gpt-5.5-pro-pre-release_high, 52.4% (OpenAI). All 101 results

  • default setting0.0%4 Dec 2025, log

Epoch's name: moonshotai/Kimi-K2-Thinking. Best closed model on this set: gdm-ai-co-mathematician, 47.9% (Google DeepMind). All 72 results

CL-benchReported

Epoch's name: moonshotai/Kimi-K2-Thinking, kimi-k2-thinking. Best closed model on this set: gpt-5.4-2026-03-05_xhigh, 27.9% (OpenAI). All 23 results

Epoch's name: kimi-k2-thinking. Best closed model on this set: claude-mythos-preview-early, 85.2% (Anthropic). All 49 results

SimpleBenchReported

Epoch's name: kimi-k2-thinking. Best closed model on this set: claude-fable-5-2_unknown, 94.9% (Anthropic). All 125 results

Epoch's name: kimi-k2-thinking. Best closed model on this set: gpt-5.5_unknown, 84.7% (OpenAI). All 202 results

WeirdMLReported

Epoch's name: kimi-k2-thinking. 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-Thinking), 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-Thinking-GGUF (converted by unsloth), 3.4k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
UD-IQ3_XXS392.7 GBfile size, 9 parts393.8 GB392.7 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:UD-IQ3_XXS
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "UD-IQ3_XXS/Kimi-K2-Thinking-UD-IQ3_XXS-*-of-00009.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q3_K_S412.7 GBfile size, 10 parts413.8 GB412.7 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q3_K_S
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q3_K_S/Kimi-K2-Thinking-Q3_K_S-*-of-00010.gguf" --local-dir Kimi-K2-Thinking-GGUF
UD-Q3_K_XL423.9 GBfile size, 10 parts424.9 GB423.9 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:UD-Q3_K_XL
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "UD-Q3_K_XL/Kimi-K2-Thinking-UD-Q3_K_XL-*-of-00010.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q3_K_M456.3 GBfile size, 11 parts457.4 GB456.3 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q3_K_M
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q3_K_M/Kimi-K2-Thinking-Q3_K_M-*-of-00011.gguf" --local-dir Kimi-K2-Thinking-GGUF
IQ4_XS509.6 GBfile size, 12 parts510.6 GB509.6 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:IQ4_XS
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "IQ4_XS/Kimi-K2-Thinking-IQ4_XS-*-of-00012.gguf" --local-dir Kimi-K2-Thinking-GGUF
IQ4_NL539.3 GBfile size, 12 parts540.3 GB539.3 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:IQ4_NL
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "IQ4_NL/Kimi-K2-Thinking-IQ4_NL-*-of-00012.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q4_0541.3 GBfile size, 13 parts542.3 GB541.3 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q4_0
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q4_0/Kimi-K2-Thinking-Q4_0-*-of-00013.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q4_K_S543.2 GBfile size, 13 parts544.3 GB543.2 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q4_K_S
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q4_K_S/Kimi-K2-Thinking-Q4_K_S-*-of-00013.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q4_K_M578.6 GBfile size, 13 parts579.6 GB578.6 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q4_K_M
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q4_K_M/Kimi-K2-Thinking-Q4_K_M-*-of-00013.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q4_1598.8 GBfile size, 13 parts599.8 GB598.8 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q4_1
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q4_1/Kimi-K2-Thinking-Q4_1-*-of-00013.gguf" --local-dir Kimi-K2-Thinking-GGUF
UD-Q4_K_XL601.9 GBfile size, 14 parts602.9 GB601.9 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:UD-Q4_K_XL
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "UD-Q4_K_XL/Kimi-K2-Thinking-UD-Q4_K_XL-*-of-00014.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q5_K_S658.5 GBfile size, 15 parts659.5 GB658.5 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q5_K_S
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q5_K_S/Kimi-K2-Thinking-Q5_K_S-*-of-00015.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q5_K_M678.7 GBfile size, 16 parts679.7 GB678.7 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q5_K_M
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q5_K_M/Kimi-K2-Thinking-Q5_K_M-*-of-00016.gguf" --local-dir Kimi-K2-Thinking-GGUF
UD-Q5_K_XL679.7 GBfile size, 16 parts680.7 GB679.7 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:UD-Q5_K_XL
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "UD-Q5_K_XL/Kimi-K2-Thinking-UD-Q5_K_XL-*-of-00016.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q6_K785.0 GBfile size, 18 parts786.1 GB785.0 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q6_K
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q6_K/Kimi-K2-Thinking-Q6_K-*-of-00018.gguf" --local-dir Kimi-K2-Thinking-GGUF
UD-Q6_K_XL818.7 GBfile size, 19 parts819.7 GB818.7 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:UD-Q6_K_XL
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "UD-Q6_K_XL/Kimi-K2-Thinking-UD-Q6_K_XL-*-of-00019.gguf" --local-dir Kimi-K2-Thinking-GGUF
Q8_01016.1 GBfile size, 23 parts1017.2 GB1016.1 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:Q8_0
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "Q8_0/Kimi-K2-Thinking-Q8_0-*-of-00023.gguf" --local-dir Kimi-K2-Thinking-GGUF
UD-Q8_K_XL1108.3 GBfile size, 25 parts1109.4 GB1108.3 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:UD-Q8_K_XL
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "UD-Q8_K_XL/Kimi-K2-Thinking-UD-Q8_K_XL-*-of-00025.gguf" --local-dir Kimi-K2-Thinking-GGUF
BF161912.2 GBfile size, 46 parts1913.2 GB1912.2 + 0.54 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Kimi-K2-Thinking-GGUF:BF16
Download
hf download unsloth/Kimi-K2-Thinking-GGUF --include "BF16/Kimi-K2-Thinking-BF16-*-of-00046.gguf" --local-dir Kimi-K2-Thinking-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLXmlx-community/Kimi-K2-Thinking612.5 GBfile size613.5 GB612.5 + 0.54 + 0.50Download page
MLX 4bitmlx-community/Kimi-K2-Thinking-4bit1150.4 GBfile size1151.4 GB1150.4 + 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-Thinking --local-dir Kimi-K2-Thinking
Other conversions (6; sizes not read)

The Hub tags 18 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

2 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
Novita$0.60$2.50256kbf16371.1 s100.0%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-Thinking:novita", "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.