ModelÜberprüftExtern

Kimi K2.7 Code GGUF

GGUF conversions of moonshotai/Kimi-K2.7-Code for llama.cpp-compatible runtimes.

Quellehuggingface.co/freakyskittle/kimi-k2.7-code-GGUF/tree/5cf1b49ddccdcb04ac4c1213cc2eedf57e285163

ArtOtherBasismodellmoonshotai/Kimi-K2.7-CodeVersionRevision 5cf1b49Verleger@freakyskittleCBewertung

Modellquelle

Art: Other
Dateigröße: 5,91–17,6 GB
Basismodell: moonshotai/Kimi-K2.7-Code
Version: vRevision 5cf1b49
Aktualisiert: 7. Okt. 2026
Verleger: @freakyskittle
Downloads: 839
Quelle: Hugging Face

Quellenbeschreibung

Kimi K2.7 Code GGUF

GGUF conversions of moonshotai/Kimi-K2.7-Code for llama.cpp-compatible runtimes.

Available files

Variant	Files	Approx local size	Status	Notes
Q8_0	`Q8_0/kimi-k2.7-code-Q8_0-00001-of-00061.gguf` ... `00061-of-00061.gguf`	~1017 GiB	Uploaded	8-bit GGUF, split into 61 shards.
Q4_K_M	`Q4_K_M/kimi-k2.7-code-Q4_K_M-00001-of-00061.gguf` ... `00061-of-00061.gguf`	~578 GiB	Uploaded	Standard high-quality 4-bit GGUF, split because the single file exceeds Hugging Face’s 500GB per-file limit.
TQ2_0	`TQ2_0/kimi-k2.7-code-TQ2_0.gguf`	~249 GiB	Uploaded	2-bit-class ternary quantization, single file.
TQ1_0	`TQ1_0/kimi-k2.7-code-TQ1_0.gguf`	~204 GiB	Uploaded	1-bit-class ternary quantization, single file.

Q6_K is not currently uploaded in this repository.

Loading split GGUF files

For split GGUF variants, download all shards for the variant into the same directory and point llama.cpp at shard 00001. llama.cpp will discover the remaining shards automatically.

Examples:

# BF16
llama-cli -m BF16/kimi-k2.7-code-BF16-00001-of-00061.gguf -p "Write a Python function for quicksort."

# Q8_0
llama-cli -m Q8_0/kimi-k2.7-code-Q8_0-00001-of-00061.gguf -p "Write a Rust HTTP server."

# Q4_K_M
llama-cli -m Q4_K_M/kimi-k2.7-code-Q4_K_M-00001-of-00061.gguf -p "Explain async/await."

Single-file variants can be loaded directly:

llama-cli -m TQ2_0/kimi-k2.7-code-TQ2_0.gguf -p "Hello"
llama-cli -m TQ1_0/kimi-k2.7-code-TQ1_0.gguf -p "Hello"

Quantization notes

BF16 was converted from the original SafeTensors using llama.cpp convert_hf_to_gguf.py with BF16 output.
Q8_0 and Q4_K_M were quantized from the BF16 GGUF source and uploaded as split GGUF shards.
TQ1_0 and TQ2_0 are llama.cpp ternary low-bit formats.
IQ1_S was not produced because llama.cpp requires an importance matrix for that quantization.
Very large variants are split to stay under Hugging Face’s individual file-size limit.

License

See LICENSE. This model uses Moonshot AI’s Modified MIT License for Kimi K2.7 Code.

Attribution

Base model by Moonshot AI: moonshotai/Kimi-K2.7-Code.

Quellen

1 Quelle

Hugging FacePrimärVersion 5cf1b49ddccdcb04ac4c1213cc2eedf57e285163

huggingface.co/freakyskittle/kimi-k2.7-code-GGUF/tree/5cf1b49ddccdcb04ac4c1213cc2eedf57e285163

Verifiziert 30. Aug.

Modellartefakte

64 Artefakte

Q4_K_M/kimi-k2.7-code-Q4_K_M-00001-of-00061.gguf

gguf · 11,4 GB · SHA-256 42146736e09e…7da3 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00002-of-00061.gguf

gguf · 10,2 GB · SHA-256 05d91ce241e2…554e · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00003-of-00061.gguf

gguf · 10,2 GB · SHA-256 449e0d1af2b1…bac5 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00004-of-00061.gguf

gguf · 10,2 GB · SHA-256 8a3193b044dd…6042 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00005-of-00061.gguf

gguf · 10,2 GB · SHA-256 7da589b7e4e4…7039 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00006-of-00061.gguf

gguf · 10,2 GB · SHA-256 5211885701ba…34c1 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00007-of-00061.gguf

gguf · 8,86 GB · SHA-256 eb3b4980f3f3…e390 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00008-of-00061.gguf

gguf · 8,86 GB · SHA-256 43ea3bae3032…e261 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00009-of-00061.gguf

gguf · 10,2 GB · SHA-256 ab2862ab25d1…593e · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00010-of-00061.gguf

gguf · 8,86 GB · SHA-256 de1aa4fe703d…e546 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00011-of-00061.gguf

gguf · 8,86 GB · SHA-256 5bc1c58b1f83…d917 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00012-of-00061.gguf

gguf · 10,2 GB · SHA-256 772b1bb0ceac…a711 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00013-of-00061.gguf

gguf · 8,86 GB · SHA-256 d1dbe8511f96…3225 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00014-of-00061.gguf

gguf · 8,86 GB · SHA-256 ef4bac0caec1…60f8 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00015-of-00061.gguf

gguf · 10,2 GB · SHA-256 15c7e2269a1e…354a · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00016-of-00061.gguf

gguf · 8,86 GB · SHA-256 51aebb6bb8b1…5e43 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00017-of-00061.gguf

gguf · 8,86 GB · SHA-256 00683112b07f…c595 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00018-of-00061.gguf

gguf · 10,2 GB · SHA-256 e3569a8363d7…0081 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00019-of-00061.gguf

gguf · 8,86 GB · SHA-256 7889b06e8000…e71e · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00020-of-00061.gguf

gguf · 8,86 GB · SHA-256 27ce2c121f65…e461 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00021-of-00061.gguf

gguf · 10,2 GB · SHA-256 0e448184fa3b…bad0 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00022-of-00061.gguf

gguf · 8,86 GB · SHA-256 fc96f9c75a50…4fa7 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00023-of-00061.gguf

gguf · 8,86 GB · SHA-256 fb67feaf7220…4406 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00024-of-00061.gguf

gguf · 10,2 GB · SHA-256 c75f4fdd5461…c3d9 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00025-of-00061.gguf

gguf · 8,86 GB · SHA-256 fb6bbf741190…48fe · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00026-of-00061.gguf

gguf · 8,86 GB · SHA-256 8d5d5ddf0bba…eb34 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00027-of-00061.gguf

gguf · 10,2 GB · SHA-256 f8e472b8f9df…885f · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00028-of-00061.gguf

gguf · 8,86 GB · SHA-256 04908c1d4583…9735 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00029-of-00061.gguf

gguf · 8,86 GB · SHA-256 4c16b35c6447…1e4e · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00030-of-00061.gguf

gguf · 10,2 GB · SHA-256 bc63e86a4acd…4cc4 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00031-of-00061.gguf

gguf · 8,86 GB · SHA-256 eb787c44c1d7…cae7 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00032-of-00061.gguf

gguf · 8,86 GB · SHA-256 3f1927af31d8…1ee7 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00033-of-00061.gguf

gguf · 10,2 GB · SHA-256 6eb287b52964…e2b5 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00034-of-00061.gguf

gguf · 8,86 GB · SHA-256 873e2a6b8a5d…d4dd · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00035-of-00061.gguf

gguf · 8,86 GB · SHA-256 c97d4557fe09…c1ba · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00036-of-00061.gguf

gguf · 10,2 GB · SHA-256 8c857710ea34…a0b2 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00037-of-00061.gguf

gguf · 8,86 GB · SHA-256 992bc6e5c5d8…ebf9 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00038-of-00061.gguf

gguf · 8,86 GB · SHA-256 ac694203a193…3e92 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00039-of-00061.gguf

gguf · 10,2 GB · SHA-256 cba38fe2249a…676d · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00040-of-00061.gguf

gguf · 8,86 GB · SHA-256 dc638a03a98c…99a0 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00041-of-00061.gguf

gguf · 8,86 GB · SHA-256 83148230b706…4a7b · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00042-of-00061.gguf

gguf · 10,2 GB · SHA-256 6f73fd327f94…af2b · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00043-of-00061.gguf

gguf · 8,86 GB · SHA-256 fa2d42e8d4e2…ff0e · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00044-of-00061.gguf

gguf · 8,86 GB · SHA-256 0ce3bf6bd383…f056 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00045-of-00061.gguf

gguf · 10,2 GB · SHA-256 c1ae231b63d7…403d · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00046-of-00061.gguf

gguf · 8,86 GB · SHA-256 b50e64b93cec…7bd5 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00047-of-00061.gguf

gguf · 8,86 GB · SHA-256 35acdc9b0a15…f704 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00048-of-00061.gguf

gguf · 10,2 GB · SHA-256 545828e82920…29c0 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00049-of-00061.gguf

gguf · 8,86 GB · SHA-256 2a07802974d0…f25d · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00050-of-00061.gguf

gguf · 8,86 GB · SHA-256 65bf77b62668…b7b3 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00051-of-00061.gguf

gguf · 10,2 GB · SHA-256 9d429142b4c4…5fc8 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00052-of-00061.gguf

gguf · 8,86 GB · SHA-256 c5e56b7001d0…e73a · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00053-of-00061.gguf

gguf · 10,2 GB · SHA-256 0e2a6b6e8158…c79a · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00054-of-00061.gguf

gguf · 10,2 GB · SHA-256 deef46913233…13ac · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00055-of-00061.gguf

gguf · 10,2 GB · SHA-256 de843a84c752…f2d7 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00056-of-00061.gguf

gguf · 10,2 GB · SHA-256 a256b06343dd…f823 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00057-of-00061.gguf

gguf · 10,2 GB · SHA-256 850c11a21874…09c7 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00058-of-00061.gguf

gguf · 10,2 GB · SHA-256 3425c2f2a495…4c27 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00059-of-00061.gguf

gguf · 10,2 GB · SHA-256 cdd4c84da444…ad9d · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00060-of-00061.gguf

gguf · 10,2 GB · SHA-256 742c327568c6…b101 · Hugging Face

Herunterladen

Q4_K_M/kimi-k2.7-code-Q4_K_M-00061-of-00061.gguf

gguf · 5,91 GB · SHA-256 ebb205f6402a…1cd4 · Hugging Face

Herunterladen

Q8_0/kimi-k2.7-code-Q8_0-00001-of-00061.gguf

gguf · 17,6 GB · SHA-256 16bc376fd9f1…2558 · Hugging Face

Herunterladen

Q8_0/kimi-k2.7-code-Q8_0-00002-of-00061.gguf

gguf · 16,7 GB · SHA-256 f90f33415091…53cb · Hugging Face

Herunterladen

Q8_0/kimi-k2.7-code-Q8_0-00003-of-00061.gguf

gguf · 16,7 GB · SHA-256 769c92ca4f87…bd41 · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge

Readme11. Julihuggingface.co/freakyskittle/kimi-k2.7-code-GGUF

--- license: other base_model: moonshotai/Kimi-K2.7-Code tags: - gguf - llama.cpp - kimi - kimi-k2.7-code - bf16 - quantized - tq1_0 - tq2_0 - q4_k_m - q8_0 library_name: gguf --- # Kimi K2.7 Code GGUF GGUF conversions of [`moonshotai/Kimi-K2.7-Code`](https://huggingface.co/moonshotai/Kimi-K2.7-Code) for llama.cpp-compatible runtimes. ## Available files | Variant | Files | Approx local size | Status | Notes | |---|---:|---:|---|---| | Q8_0 | `Q8_0/kimi-k2.7-code-Q8_0-00001-of-00061.gguf` ... `00061-of-00061.gguf` | ~1017 GiB | Uploaded | 8-bit GGUF, split into 61 shards. | | Q4_K_M | `Q4_K_M/kimi-k2.7-code-Q4_K_M-00001-of-00061.gguf` ... `00061-of-00061.gguf` | ~578 GiB | Uploaded | Standard high-quality 4-bit GGUF, split because the single file exceeds Hugging Face’s 500GB per-file limit. | | TQ2_0 | `TQ2_0/kimi-k2.7-code-TQ2_0.gguf` | ~249 GiB | Uploaded | 2-bit-class ternary quantization, single file. | | TQ1_0 | `TQ1_0/kimi-k2.7-code-TQ1_0.gguf` | ~204 GiB | Uploaded | 1-bit-class ternary quantization, single file. | `Q6_K` is not currently uploaded in this repository. ## Loading split GGUF files For split GGUF variants, download all shards for the variant into the same directory and point llama.cpp at shard `00001`. llama.cpp will discover the remaining shards automatically. Examples: ```bash # BF16 llama-cli -m BF16/kimi-k2.7-code-BF16-00001-of-00061.gguf -p "Write a Python function for quicksort." # Q8_0 llama-cli -m Q8_0/kimi-k2.7-code-Q8_0-00001-of-00061.gguf -p "Write a Rust HTTP server." # Q4_K_M llama-cli -m Q4_K_M/kimi-k2.7-code-Q4_K_M-00001-of-00061.gguf -p "Explain async/await." ``` Single-file variants can be loaded directly: ```bash llama-cli -m TQ2_0/kimi-k2.7-code-TQ2_0.gguf -p "Hello" llama-cli -m TQ1_0/kimi-k2.7-code-TQ1_0.gguf -p "Hello" ``` ## Quantization notes - `BF16` was converted from the original SafeTensors using llama.cpp `convert_hf_to_gguf.py` with BF16 output. - `Q8_0` and `Q4_K_M` were quantized from the BF16 GGUF source and uploaded as split GGUF shards. - `TQ1_0` and `TQ2_0` are llama.cpp ternary low-bit formats. - `IQ1_S` was not produced because llama.cpp requires an importance matrix for that quantization. - Very large variants are split to stay under Hugging Face’s individual file-size limit. ## License See [`LICENSE`](./LICENSE). This model uses Moonshot AI’s Modified MIT License for Kimi K2.7 Cod...

Note30. Aug.huggingface.co/freakyskittle/kimi-k2.7-code-GGUF

Source context: 839 downloads · 5 likes · Library gguf · Repo freakyskittle/kimi-k2.7-code-GGUF

Note17. Julihuggingface.co/freakyskittle/kimi-k2.7-code-GGUF

Source context: 4264 downloads · 5 likes · Library gguf · Repo freakyskittle/kimi-k2.7-code-GGUF