- Size
- 1.0T parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: unsloth/Kimi-K2.7-Code-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
- 11 Jun 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-K2.7-Code323k downloads in the last 30 days, 1.4k likes
Scores
- default setting14.0%±3.513 Oct 2026, log
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-fable-5-2_max, 79.0% (Anthropic). All 166 results
- default setting12.2%±5.213 Jun 2026, log
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-fable-5-2_max, 100.0% (Anthropic). All 83 results
- default setting54.0%±3.013 Jun 2026, log
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-fable-5-2_max, 95.1% (Anthropic). All 127 results
- default setting87.9%±2.37 Aug 2026, log
Epoch's name: kimi-k2.7-code. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting95.6%±3.17 Aug 2026, log
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results
- default setting36.5%±1.527 Aug 2026, log
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-fable-5-2_max, 94.0% (Anthropic). All 105 results
- default setting37.6%via Epoch AI (error bar left out)
Epoch's name: kimi-k2.7-code. Best closed model on this set: gemini-4-carbon_unknown, 84.2% (Google DeepMind). All 66 results
- default setting10.0%via Epoch AI
Epoch's name: kimi-k2.7-code. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- Harness: mini-swe-agent30.5%30.0 to 31.0deepswe.datacurve.ai
Epoch's name: kimi-k2.7-code. Best closed model on this set: gpt-6-astra_xhigh, 74.1% (OpenAI). All 69 results
- Harness: mini-swe-agent; Reasoning effort: none30.1%cognition.com
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-opus-5-5_medium, 54.6% (Anthropic). All 46 results
- default setting0.9%21 Jun 2026, gbaeval.com
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-opus-5-5_unknown, 90.6% (Anthropic). All 28 results
- default setting57.9%lmcouncil.ai
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-fable-5-2_unknown, 94.9% (Anthropic). All 125 results
- default setting48.8%yhenon.github.io
Epoch's name: kimi-k2.7-code. Best closed model on this set: claude-fable-5_high, 95.0% (Anthropic). All 29 results
- default setting54.1%±0.0htihle.github.io
Epoch's name: kimi-k2.7-code. 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
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-K2.7-Code), 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-K2.7-Code-GGUF (converted by unsloth), 21k 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.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| UD-IQ1_M | 283.0 GBfile size, 8 parts | 284.1 GB283.0 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_MDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-IQ1_M/Kimi-K2.7-Code-UD-IQ1_M-*-of-00008.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-IQ2_XXS | 296.0 GBfile size, 8 parts | 297.0 GB296.0 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-IQ2_XXSDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-IQ2_XXS/Kimi-K2.7-Code-UD-IQ2_XXS-*-of-00008.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-IQ2_M | 296.1 GBfile size, 8 parts | 297.2 GB296.1 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-IQ2_MDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-IQ2_M/Kimi-K2.7-Code-UD-IQ2_M-*-of-00008.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-Q2_K_XL | 316.2 GBfile size, 8 parts | 317.2 GB316.2 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-Q2_K_XLDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-Q2_K_XL/Kimi-K2.7-Code-UD-Q2_K_XL-*-of-00008.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-IQ3_S | 390.0 GBfile size, 10 parts | 391.1 GB390.0 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-IQ3_SDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-IQ3_S/Kimi-K2.7-Code-UD-IQ3_S-*-of-00010.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-Q3_K_M | 431.8 GBfile size, 11 parts | 432.8 GB431.8 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-Q3_K_MDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-Q3_K_M/Kimi-K2.7-Code-UD-Q3_K_M-*-of-00011.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-Q3_K_XL | 432.0 GBfile size, 11 parts | 433.1 GB432.0 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-Q3_K_XLDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-Q3_K_XL/Kimi-K2.7-Code-UD-Q3_K_XL-*-of-00011.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-IQ4_XS | 461.1 GBfile size, 12 parts | 462.1 GB461.1 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-IQ4_XSDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-IQ4_XS/Kimi-K2.7-Code-UD-IQ4_XS-*-of-00012.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-Q4_K_XL | 543.6 GBfile size, 14 parts | 544.7 GB543.6 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-Q4_K_XLDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-Q4_K_XL/Kimi-K2.7-Code-UD-Q4_K_XL-*-of-00014.gguf" --local-dir Kimi-K2.7-Code-GGUF |
| UD-Q8_K_XL | 553.7 GBfile size, 14 parts | 554.7 GB553.7 + 0.54 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-Q8_K_XLDownload hf download unsloth/Kimi-K2.7-Code-GGUF --include "UD-Q8_K_XL/Kimi-K2.7-Code-UD-Q8_K_XL-*-of-00014.gguf" --local-dir Kimi-K2.7-Code-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 6bitspicyneuron/Kimi-K2.7-Code-MLX-3.6bit | 427.6 GBfile size | 428.6 GB427.6 + 0.54 + 0.50 | Download page |
| MLXmlx-community/Kimi-K2.7-Code-mlx-DQ3_K_M-q8 | 438.3 GBfile size | 439.3 GB438.3 + 0.54 + 0.50 | Download 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-K2.7-Code --local-dir Kimi-K2.7-CodeOther conversions (5; sizes not read)
- nvidia/Kimi-K2.7-Code-NVFP4 NVFP4, 1.9k downloads
- amd/Kimi-K2.7-Code-MXFP4 Other, mxfp4, 550 downloads
- unsloth/Kimi-K2.7-Code Other, 301 downloads
- rAVEUK/Kimi-K2.7-Code Other, 44 downloads
- decart-ai/Kimi-K2.7-Code-NVFP4 NVFP4, 34 downloads
The Hub tags 29 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
9 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.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| CoreWeave | $0.60 | $3.00 | 256k | int4 | 108 | 0.8 s | 99.3% | yes | yes |
| deepinfra | $0.68 | $3.40 | 256k | not given | 43 | 0.8 s | ? | yes | yes |
| Inceptron | $0.66 | $3.50 | 256k | int4 | 65 | 0.8 s | 100.0% | yes | yes |
| Venice | $0.75 | $3.50 | 250k | int4 | 43 | 2.9 s | 100.0% | yes | yes |
| SiliconFlow | $0.86 | $3.80 | 256k | fp8 | 12 | 4.1 s | 100.0% | yes | no |
| Novita | $0.91 | $3.84 | 256k | int4 | 32 | 2.1 s | 100.0% | yes | yes |
| Cloudflare | $0.95 | $4.00 | 256k | not given | 31 | 1.3 s | 100.0% | yes | yes |
| Moonshot AIthe maker | $0.95 | $4.00 | 256k | not given | 27 | 1.8 s | 99.8% | yes | yes |
| featherless-ai | ? | ? | ? | not given | ? | ? | ? | not given | not 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-K2.7-Code:coreweave", "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
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- nvidia/Kimi-K2.7-Code-DFlash3.5B392Unreviewed
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.