KI

Kimi-Dev-72B

KimiGGUF by unslothUpdated 2025-06-17
Download on Hugging Face
Parameters72.7B
Context128K
Layers80
Architectureqwen2
Smallest quant23.0 GB
Quick answer

Kimi-Dev-72B needs about 42.9 GB of memory at IQ4_XS (a 39.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 19 quants, from 23.0 GB (IQ1_S) to 145.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Kimi-Dev-72B: 72.7B parameter coding LLM

Kimi-Dev-72B is a 72.7B parameter model optimized for software engineering tasks. It is open‑source under the MIT license and supports a 131072 token context window. The model excels at coding and code repair.

Good at

  • Large context handling
  • Coding tasks
  • Code repair

Limits

  • No vision support
  • Large VRAM requirement for full precision
  • Requires 8k context for memory estimates

Best for

  • Automated code patching
  • SWE‑bench verification
  • Docker‑based repository testing

Who it’s for. Developers and researchers needing a high‑capacity coding model. The model is suitable for teams building code‑generation tools or conducting research on software repair.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S23.0 GB 26.2 GB
Too big Get file →
IQ1_M24.0 GB 27.2 GB
Too big Get file →
IQ2_XXS25.7 GB 28.9 GB
Too big Get file →
IQ2_M29.6 GB 32.8 GB
Too big Get file →
Q2_K_XL30.3 GB 33.5 GB
Too big Get file →
IQ3_XXS31.9 GB 35.0 GB
Too big Get file →
Q3_K_S34.5 GB 37.7 GB
Too big Get file →
Q3_K_M37.7 GB 40.9 GB
Too big Get file →
Q3_K_XL38.3 GB 41.5 GB
Too big Get file →
IQ4_XS39.7 GB 42.9 GB
Too big Get file →
IQ4_NL41.3 GB 44.5 GB
Too big Get file →
Q4_041.4 GB 44.6 GB
Too big Get file →
Q4_145.7 GB 48.9 GB
Too big Get file →
Q5_K_XL54.1 GB (2 parts) 57.3 GB
Too big Get file →
Q6_K64.3 GB (2 parts) 67.5 GB
Too big Get file →
Q6_K_XL67.2 GB (2 parts) 70.3 GB
Too big Get file →
Q8_077.3 GB (2 parts) 80.4 GB
Too big Get file →
Q8_K_XL84.0 GB (2 parts) 87.2 GB
Too big Get file →
BF16145.4 GB (3 parts) 148.6 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (23.05 GB file, 26.2 GB memory at 8k context). For 16 GB VRAM, IQ4_XS (39.75 GB file, 42.9 GB memory) is a good balance. For 32 GB VRAM, Q6_K (64.35 GB file, 67.5 GB memory) offers higher precision.

What GPU do you need for Kimi-Dev-72B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ2_XXS (25.7 GB file, about 28.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_0 (41.4 GB file, about 44.6 GB in use).

Which Kimi-Dev-72B quant should you choose?

IQ4_XS (39.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ1_S at 23.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters72.7B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byunsloth
FamilyKimi
Licensemit
Downloads (HF)3,532
Last updated2025-06-17

Frequently asked questions about Kimi-Dev-72B

How much VRAM does Kimi-Dev-72B need?

About 42.9 GB at IQ4_XS with an 8K context window. That is the 39.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Kimi-Dev-72B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kimi-Dev-72B GGUF?

It depends on the quant: IQ1_S is 23.0 GB, IQ1_M is 24.0 GB, IQ2_XXS is 25.7 GB, IQ2_M is 29.6 GB, Q2_K_XL is 30.3 GB, IQ3_XXS is 31.9 GB and 13 more.

What context length does Kimi-Dev-72B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Kimi-Dev-72B GGUF?

The files are on Hugging Face in the unsloth/Kimi-Dev-72B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Kimi-Dev-72B use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Kimi-Dev-72B on 8 GB VRAM?

Only the IQ1_S quant can fit on 8 GB VRAM, but it still requires about 26.2 GB of memory at 8k context, so it is not feasible without further optimization.

Does Kimi-Dev-72B support image input?

No, the model has no vision capabilities.

Other GGUFs of Kimi-Dev-72B

Similar models

Browse all →

More from unsloth

All by unsloth →

More Kimi models

All Kimi →

Other large models

All large models →