moonshotai Kimi K2.6 needs about 403.0 GB of memory at Q2_K_L (a 359.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 17 quants, from 1.5 GB to 583.7 GB (Q4_0).
Kimi K2.6 – 1.03 B deepseek2 model with 262,144‑token context
Kimi K2.6 is a 1.03 B parameter deepseek2 model with a 262,144‑token context window. It is available in multiple GGUF quantizations, ranging from 1.53 GB to 583.71 GB. The model supports long‑horizon coding and agentic tasks.
Good at
- Long‑horizon coding
- Agent swarm orchestration
- Coding‑driven design
Limits
- No vision support
- Large memory requirement for higher quants
- License is other
Best for
- Code generation with long context
- Autonomous task orchestration
- Design generation from prompts
Who it’s for. Developers and researchers needing a large‑context LLM for coding and agentic workflows. The model is open‑source and can be run with llama.cpp or compatible tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.5 GB | 2.2 GB | Fits | Get file → | |
| IQ1_S | 207.4 GB (6 parts) | 232.8 GB | Too big | Get file → | |
| IQ1_M | 232.4 GB (6 parts) | 260.8 GB | Too big | Get file → | |
| IQ2_XXS | 271.5 GB (7 parts) | 304.5 GB | Too big | Get file → | |
| IQ2_XS | 303.2 GB (8 parts) | 340.1 GB | Too big | Get file → | |
| IQ2_S | 308.8 GB (8 parts) | 346.3 GB | Too big | Get file → | |
| IQ2_M | 341.7 GB (9 parts) | 383.2 GB | Too big | Get file → | |
| Q2_K | 358.2 GB (10 parts) | 401.7 GB | Too big | Get file → | |
| Q2_K_L | 359.3 GB (10 parts) | 403.0 GB | Too big | Get file → | |
| IQ3_XXS | 426.6 GB (11 parts) | 478.3 GB | Too big | Get file → | |
| Q3_K_S | 444.4 GB (12 parts) | 498.2 GB | Too big | Get file → | |
| IQ3_XS | 466.4 GB (13 parts) | 522.9 GB | Too big | Get file → | |
| Q3_K_M | 466.9 GB (13 parts) | 523.4 GB | Too big | Get file → | |
| Q3_K_L | 487.5 GB (13 parts) | 546.5 GB | Too big | Get file → | |
| IQ3_M | 488.1 GB (13 parts) | 547.1 GB | Too big | Get file → | |
| Q3_K_XL | 488.6 GB (13 parts) | 547.7 GB | Too big | Get file → | |
| Q4_0 | 583.7 GB (16 parts) | 654.3 GB | Too big | Get file → |
For 8 GB VRAM, use the 1.53 GB unknown quant (≈2.2 GB memory at 8k context). For 16 GB VRAM, the IQ1_S (207.4 GB) or IQ1_M (232.43 GB) quants are suitable, requiring ≈232.8 GB or 260.8 GB memory at 8k context. For 32 GB VRAM, the Q2_K (358.19 GB) or Q3_K_S (444.38 GB) quants are recommended, with ≈401.7 GB or 498.2 GB memory at 8k context.
What GPU do you need for moonshotai Kimi K2.6?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (1.5 GB file, about 2.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (1.5 GB file, about 2.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (1.5 GB file, about 2.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (1.5 GB file, about 2.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (1.5 GB file, about 2.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (1.5 GB file, about 2.2 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (1.5 GB file, about 2.2 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (1.5 GB file, about 2.2 GB in use).
Which moonshotai Kimi K2.6 quant should you choose?
Q2_K_L (359.3 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is the first one in the table at 1.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about moonshotai Kimi K2.6
How much VRAM does moonshotai Kimi K2.6 need?
About 403.0 GB at Q2_K_L with an 8K context window. That is the 359.3 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 moonshotai Kimi K2.6 on an 8 GB GPU?
Yes, with the smaller files: the 1.5 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of moonshotai Kimi K2.6 GGUF?
It depends on the quant: file is 1.5 GB, IQ1_S is 207.4 GB, IQ1_M is 232.4 GB, IQ2_XXS is 271.5 GB, IQ2_XS is 303.2 GB, IQ2_S is 308.8 GB and 11 more.
What context length does moonshotai Kimi K2.6 support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download moonshotai Kimi K2.6 GGUF?
The files are on Hugging Face in the bartowski/moonshotai_Kimi-K2.6-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 moonshotai Kimi K2.6 use?
Hugging Face lists the license as other. 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 K2.6 on 8 GB VRAM?
Use the 1.53 GB unknown quant; it requires about 2.2 GB memory at 8k context, which fits within 8 GB VRAM.
What is the largest quant I can run on 32 GB VRAM?
The Q3_K_S quant is 444.38 GB and needs about 498.2 GB memory at 8k context, which is within 32 GB VRAM limits.
Does Kimi K2.6 support vision?
No, the model does not include vision capabilities.