Kimi GGUF models

439 GGUF models in the Kimi family, quantized by 120 uploaders. Sizes run from 2M to 5376B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
KI
Kimi-K3
Kimi · unsloth
Params2780B
Context1024K
Smallest466.4 GB
Vision
KI
Kimi-K2.7-Code
Kimi · unsloth
Params1030B
Context256K
Smallest303.9 GB
CodingVision
KI
Kimi Linear 48B A3B Instruct
Kimi · bartowski
Params49.1B
Context1024K
Q4_K_M30.1 GB
GGUF
KI
Kimi-K2-Instruct
Kimi · unsloth
Params1030B
Context128K
Q4_K_M620.8 GB
Coding
KI
Kimi-K2.5
Kimi · unsloth
Params1030B
Context256K
Q4_K_M621.2 GB
GGUF
KI
MythoMax L2 Kimiko v2 13B
Kimi · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
KI
Kimi VL A3B Instruct
Kimi · mradermacher
Params16B
Context128K
Q4_K_M10.5 GB
Vision
KI
Kimi VL A3B Thinking 2506
Kimi · ggml-org
Params16B
Context128K
Q4_K_M10.5 GB
ReasoningVision
KI
Kimi-K2.6
Kimi · unsloth
Params1030B
Context256K
Smallest340.5 GB
Vision
KI
Kimi-K2-Thinking
Kimi · unsloth
Params1030B
Context256K
Q4_K_M621.2 GB
Reasoning
KI
Huihui Kimi Linear 48B A3B Instruct Abliterated
Kimi · mradermacher
Params49.1B
Context1024K
Q4_K_M29.7 GB
GGUF
KI
Kimi-Dev-72B
Kimi · unsloth
Params72.7B
Context128K
Smallest23.0 GB
Coding
KI
Kimi K3 Uncensored
Kimi · Ryanchen911
Params2780B
Context1024K
Smallest579.5 GB
GGUF
KI
Huihui Kimi Linear 48B A3B Instruct Abliterated
Kimi · mradermacher
Params49.1B
Context1024K
Q4_K_M29.7 GB
GGUF
KI
Kimi K3
Kimi · AtomicChat
Params2780B
Context1024K
Smallest589.5 GB
ReasoningTool useVision
KI
Qwopus3.5 122B A10B Kimi K2.6 destill healed abliterated
Kimi · OpenYourMind
Params125B
Context256K
Q4_K_M75.8 GB
Vision
KI
Kimi-K3
Kimi · hellohazime
Params1810B
Context1024K
Smallest441.4 GB
GGUF
KI
Kimiko v2 13B
Kimi · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
KI
Kimid V4A Q235 2k
Kimi · mradermacher
Params235B
Context256K
Q4_K_M142.2 GB
Tool use
KI
Kimi K3
Kimi · Blackfrost-AI
Params2780B
Context1024K
Smallest1009.5 GB
ReasoningTool use
KI
moonshotai Kimi K2 Thinking
Kimi · bartowski
Params1030B
Context256K
Q4_K_M624.0 GB
Reasoning
KI
Kimi K2.5
Kimi · bartowski
Params1030B
Context256K
Q4_K_M580.4 GB
Vision
KI
Kimi Linear REAP 35B A3B Instruct i1
Kimi · mradermacher
Params35B
Context1024K
Q4_K_M21.3 GB
GGUF
KI
Kimi Dev 72B
Kimi · bartowski
Params72.7B
Context128K
Smallest23.7 GB
GGUF
KI
Huihui Kimi Linear 48B A3B Instruct Abliterated
Kimi · therickcain
Params49.1B
Context1024K
Q4_K_M29.7 GB
Tool use
KI
Qwopus3.5 122B A10B Kimi K2.6 Destill Healed Abliterated
Kimi · mradermacher
Params125B
Context256K
Q4_K_M75.8 GB
Vision
KI
MythoMax Kimiko Mix
Kimi · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
KI
Kimi Linear 48B A3B Instruct
Kimi · mradermacher
Params49.1B
Context1024K
Q4_K_M29.7 GB
GGUF
KI
Kimi-K2-Instruct-0905
Kimi · unsloth
Params1030B
Context256K
Q4_K_M621.2 GB
GGUF
KI
Kimi VL A3B Instruct
Kimi · mradermacher
Params16B
Context128K
Q4_K_M10.5 GB
Vision

About the Kimi GGUF models

Kimi is represented on ggufmodels.com by 439 GGUF models, quantized by 120 uploaders on Hugging Face. The most downloaded are Kimi-K3, Kimi-K2.7-Code and Kimi Linear 48B A3B Instruct. Parameter counts run from 2M to 5376B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Kimi model is between 0.1 to 624.0 GB, which is the quant most people start with. Most files come from Thireus (185), mradermacher (59) and DevQuasar (15). The quants you will meet most often are Q2_K (127), Q4_K_M (123), Q3_K_M (116) and Q6_K (107), where the number is how many models offer that quant.

Frequently asked questions

Which Kimi GGUF should I download?

The most downloaded Kimi GGUF here is Kimi-K3. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Kimi model need?

Q4_K_M files of Kimi models on this site range from 0.1 to 624.0 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Kimi GGUF files come from?

The most common quantizers here are Thireus, mradermacher and DevQuasar. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing