Kimi VL A3B Instruct needs about 11.5 GB of memory at Q4_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 14.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Kimi VL A3B Instruct – a vision‑language model with 16B parameters and 128K context
Kimi VL A3B Instruct is a 16B parameter vision‑language model that supports long‑context reasoning up to 131072 tokens. It uses a native‑resolution visual encoder and a Mixture‑of‑Experts language decoder. The model is released under the MIT license.
Good at
- Long‑context multimodal reasoning
- High‑resolution image understanding
- Agent‑style multi‑turn interactions
Limits
- No vision support in non‑vision variants
- Requires large VRAM for higher‑quality quants
- No explicit language‑only mode
Best for
- Developing multimodal agents
- Processing long documents or videos
- Fine‑tuning on vision‑language tasks
Who it’s for. Engineers and researchers building multimodal applications who need a lightweight yet powerful VLM. The model is suitable for developers who can run it on GPUs with sufficient VRAM and are comfortable with GGUF quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 5.1 GB | 6.1 GB | Fits | Get file → | |
| IQ1_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| IQ2_XXS | 5.8 GB | 6.8 GB | Fits | Get file → | |
| IQ2_XS | 6.1 GB | 7.1 GB | Fits | Get file → | |
| IQ2_S | 6.2 GB | 7.1 GB | Fits | Get file → | |
| IQ2_M | 6.5 GB | 7.5 GB | Tight | Get file → | |
| Q2_K | 6.6 GB | 7.6 GB | Tight | Get file → | |
| Q2_K_S | 6.6 GB | 7.6 GB | Tight | Get file → | |
| IQ3_XXS | 7.1 GB | 8.1 GB | Too big | Get file → | |
| IQ3_XS | 7.3 GB | 8.3 GB | Too big | Get file → | |
| IQ3_S | 7.6 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_S | 7.6 GB | 8.6 GB | Too big | Get file → | |
| IQ3_M | 7.7 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 8.3 GB | 9.3 GB | Too big | Get file → | |
| Q3_K_L | 8.6 GB | 9.6 GB | Too big | Get file → | |
| IQ4_XS | 8.7 GB | 9.7 GB | Too big | Get file → | |
| IQ4_NL | 9.1 GB | 10.1 GB | Too big | Get file → | |
| Q4_0 | 9.1 GB | 10.1 GB | Too big | Get file → | |
| Q4_K_S | 9.7 GB | 10.7 GB | Too big | Get file → | |
| Q4_1 | 10.1 GB | 11.0 GB | Too big | Get file → | |
| Q4_K_M | 10.5 GB | 11.5 GB | Too big | Get file → | |
| Q5_K_S | 11.3 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_M | 12.0 GB | 13.0 GB | Too big | Get file → | |
| Q6_K | 14.3 GB | 15.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (5.13 GB, 6.1 GB memory at 8K context). For 12 GB VRAM, IQ2_M (6.48 GB, 7.5 GB memory) or Q2_K (6.58 GB, 7.6 GB memory). For 16 GB VRAM, Q3_K_M (8.29 GB, 9.3 GB memory) or Q4_K_M (10.54 GB, 11.5 GB memory) provide a balance of size and performance. Estimates are approximate.
What GPU do you need for Kimi VL A3B Instruct?
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: the best quant that fits is the main file (0.0 GB file, about 1.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_S (6.6 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (10.5 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (14.3 GB file, about 15.3 GB in use).
Which Kimi VL A3B Instruct quant should you choose?
Q4_K_M is the usual starting point for Kimi VL A3B Instruct: it balances file size and quality well. Here it is a 10.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 Kimi VL A3B Instruct
How much VRAM does Kimi VL A3B Instruct need?
About 11.5 GB at Q4_K_M with an 8K context window. That is the 10.5 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 VL A3B Instruct on an 8 GB GPU?
Yes, with Q2_K_S: the 6.6 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kimi VL A3B Instruct GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 5.1 GB, IQ1_M is 5.4 GB, IQ2_XXS is 5.8 GB, IQ2_XS is 6.1 GB, IQ2_S is 6.2 GB and 19 more.
What context length does Kimi VL A3B Instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download Kimi VL A3B Instruct GGUF?
The files are on Hugging Face in the mradermacher/Kimi-VL-A3B-Instruct-i1-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 VL A3B Instruct 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 VL A3B Instruct on 8 GB VRAM?
Yes, the IQ1_S quant (5.13 GB file) uses about 6.1 GB VRAM at 8K context, which fits within 8 GB.
Does the model support vision tasks?
Yes, it includes a native‑resolution visual encoder and is designed for vision‑language tasks.
What license does the model use?
The model is released under the MIT license.