How much memory do I need to run Kimi-K2.7-Code (UD-IQ1_M)?

The file size is 304 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 305 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.

Does Kimi-K2.7-Code run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?

8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: no quantization fits (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).

What is the command to run Kimi-K2.7-Code with Ollama?

Run "ollama run hf.co/unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.

moonshotai

Kimi-K2.7-Code

Image input

Parameters: 1,026.4B
Max context length: 262,144
Architecture: deepseek2
License: Conditional

Base model: moonshotai/Kimi-K2.7-Code
License: modified-mit

Memory needed to run UD-IQ1_M at 8K tokens

305 GB Estimated

File size 304 GB Measured

VRAM it fits in (rough guide)

8 GB does not fit
12 GB does not fit
16 GB does not fit
24 GB does not fit
32 GB does not fit
48 GB does not fit

Macs cap how much memory the GPU can use, so leave headroom in unified memory.

Data as of Nov 10, 2026

About Kimi-K2.7-Code

Kimi-K2.7-Code is a GGUF model based on moonshotai/Kimi-K2.7-Code on Hugging Face. GGUF files are published by unsloth/Kimi-K2.7-Code-GGUF. It has about 1,026.4B parameters, the deepseek2 architecture, a maximum context length of 262,144 tokens (values written in the GGUF).

There are 10 quantizations, with file sizes from 304 GB (UD-IQ1_M) to 595 GB (UD-Q8_K_XL) (actual sizes on Hugging Face).

Running UD-IQ1_M (304 GB) with an 8,192-token context needs an estimated 305 GB of memory, and an estimated 307 GB at 32,768 tokens.

The original model is licensed under Modified MIT License (Moonshot AI's Kimi), which allows commercial use with conditions such as scale or purpose. Check the original license for the terms of use. An mmproj file for image input is also available.

File size and estimated memory per quantization

Up to 8 GB
Up to 16 GB
Up to 24 GB
Up to 48 GB
Up to 128 GB
More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

Using image input: This model supports image input. To use images, an mmproj file is loaded as well.

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization	Quality guide	KLD (no imatrix)	KLD (imatrix)	Size (Llama-3-8B)
Q8_0	Nearly identical	0.0014	-	7.96 GiB
Q6_K	Very small	0.0055	-	6.14 GiB
Q5_K_M	Very small	0.0108	-	5.33 GiB
Q5_K_S	Small	0.0166	-	5.21 GiB
Q5_1	Small	0.0180	-	5.65 GiB
Q5_0	Small	0.0222	-	5.21 GiB
Q4_K_M	Small	0.0313	0.0282	4.58 GiB
Q4_K_S	Medium	0.0431	0.0320	4.37 GiB
IQ4_NL	Small	-	0.0357	4.35 GiB
IQ4_XS	Small	-	0.0363	4.14 GiB
Q4_1	Medium	0.0717	-	4.78 GiB
Q4_0	Medium	0.0719	-	4.34 GiB
Q3_K_L	Medium	0.0872	0.0731	4.03 GiB
Q3_K_M	Medium	0.1019	0.0844	3.74 GiB
IQ3_M	Medium	-	0.1025	3.53 GiB
IQ3_S	Medium	-	0.1113	3.42 GiB
IQ3_XS	Large	-	0.1387	3.28 GiB
IQ3_XXS	Large	-	0.1836	3.05 GiB
Q3_K_S	Large	0.2282	0.1998	3.41 GiB
IQ2_M	Large	-	0.3260	2.74 GiB
Q2_K	Very large	0.4451	0.3322	2.96 GiB
Q2_K_S	Very large	-	0.4034	2.96 GiB
IQ2_S	Very large	-	0.4392	2.56 GiB
IQ2_XS	Very large	-	0.5463	2.43 GiB
IQ2_XXS	Very large	-	0.8120	2.24 GiB
IQ1_M	Very large	-	1.3931	2.01 GiB
IQ1_S	Very large	-	2.2546	1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

unsloth/Kimi-K2.7-Code-GGUF

Converted and published by a third party About this label

Last checked: Nov 10, 2026

Architecture: deepseek2; Supported before llama.cpp b4409
Parameters: 1,026.4B
Max context length: 262,144
License: modified-mit Conditional

File size and memory per quantization for Kimi-K2.7-Code (unsloth/Kimi-K2.7-Code-GGUF)
Quantization	File size Measured	Quality guide	4,096	8,192	16,384	32,768	65,536	131,072	262,144 max
UD-IQ1_M (8 parts)	304 GB	-	305 GB	305 GB	306 GB	307 GB	309 GB	314 GB	323 GB
UD-IQ2_XXS (8 parts)	318 GB	-	319 GB	319 GB	320 GB	321 GB	323 GB	328 GB	337 GB
UD-IQ2_M (8 parts)	318 GB	-	319 GB	319 GB	320 GB	321 GB	323 GB	328 GB	337 GB
UD-Q2_K_XL (8 parts)	339 GB	-	341 GB	341 GB	341 GB	343 GB	345 GB	350 GB	359 GB
UD-IQ3_S (10 parts)	419 GB	-	420 GB	420 GB	421 GB	422 GB	424 GB	429 GB	438 GB
UD-Q3_K_M (11 parts)	464 GB	-	465 GB	465 GB	466 GB	467 GB	469 GB	474 GB	483 GB
UD-Q3_K_XL (11 parts)	464 GB	-	465 GB	465 GB	466 GB	467 GB	469 GB	474 GB	483 GB
UD-IQ4_XS (12 parts)	495 GB	-	496 GB	497 GB	497 GB	498 GB	501 GB	505 GB	514 GB
UD-Q4_K_XL (14 parts)	584 GB	-	585 GB	585 GB	586 GB	587 GB	589 GB	594 GB	603 GB
UD-Q8_K_XL (14 parts)	595 GB	-	596 GB	596 GB	597 GB	598 GB	600 GB	605 GB	614 GB

The mmproj file for image input (F16) is 0.95 GB Measured . It is not included in the memory above, so add it if you use images.

Ollama  ollama run hf.co/unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_M

llama.cpp  llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_M

Third-party evaluations

Values from other organizations for the original model before quantization. Not this site's own rating. Values are for the original model before quantization. GGUF quantization (especially small quantizations) can lower performance.

Capabilities (Epoch AI)

151.1 149.1–153.2

Kimi K2.7 Code · Values as of Jun 12, 2026

Source: Epoch Capabilities Index (Epoch AI) (CC BY 4.0). Original leaderboard · See in ranking

Hard science (GPQA)

87.9% 83.3%–92.4%

kimi-k2.7-code · Values as of Aug 7, 2026

Source: GPQA Diamond (Epoch AI) (CC BY 4.0). Original leaderboard · See in ranking

License and commercial use

Modified MIT License (Moonshot AI's Kimi) Conditional

MIT License plus one condition. If a commercial product or service has more than 100 million monthly active users or more than US$20 million in monthly revenue, the model name (Kimi K2, Kimi K2.6, Kimi K2.7 Code, etc.) must be prominently displayed in its interface. Otherwise it is like MIT: keep the copyright notice and license text. We checked the original text of Moonshot AI's Kimi K2, K2.6 and K2.7 Code; other authors using the same name may have different terms.

Based on the license on the original model's Hugging Face page. Original license text (checked Nov 1, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Example commands using UD-IQ1_M. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_M

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_M

LM Studio

Paste unsloth/Kimi-K2.7-Code-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run Kimi-K2.7-Code (UD-IQ1_M)?: The file size is 304 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 305 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can Kimi-K2.7-Code be used commercially?: The original model's license is Modified MIT License (Moonshot AI's Kimi) (Commercial use with conditions).MIT License plus one condition. If a commercial product or service has more than 100 million monthly active users or more than US$20 million in monthly revenue, the model name (Kimi K2, Kimi K2.6, Kimi K2.7 Code, etc.) must be prominently displayed in its interface. Otherwise it is like MIT: keep the copyright notice and license text. We checked the original text of Moonshot AI's Kimi K2, K2.6 and K2.7 Code; other authors using the same name may have different terms. Check the original license text before deciding.
Does Kimi-K2.7-Code run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?: 8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: no quantization fits (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run Kimi-K2.7-Code with Ollama?: Run "ollama run hf.co/unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.