Pixtral 12B 2409 hf text only needs about 16.1 GB of memory at Q8_0 (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 9.2 GB (Q4_K_L) to 24.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Pixtral 12B 2409 hf text only is a 12.2B-parameter Pixtral model in GGUF format, quantized by leafspark. Its trained context length is 1000K tokens. The repository has 3 quant files, from 9.2 GB (Q4_K_L) to 24.5 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_L | 9.2 GB | 11.1 GB | Too big | Get file → | |
| Q8_0 | 14.3 GB | 16.1 GB | Too big | Get file → | |
| BF16 | 24.5 GB | 26.3 GB | Too big | Get file → |
What GPU do you need for Pixtral 12B 2409 hf text only?
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: the best quant that fits is Q4_K_L (9.2 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_L (9.2 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.3 GB file, about 16.1 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (24.5 GB file, about 26.3 GB in use).
Which Pixtral 12B 2409 hf text only quant should you choose?
Q8_0 (14.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q4_K_L at 9.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Pixtral 12B 2409 hf text only
How much VRAM does Pixtral 12B 2409 hf text only need?
About 16.1 GB at Q8_0 with an 8K context window. That is the 14.3 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 Pixtral 12B 2409 hf text only on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Pixtral 12B 2409 hf text only GGUF?
It depends on the quant: Q4_K_L is 9.2 GB, Q8_0 is 14.3 GB, BF16 is 24.5 GB.
What context length does Pixtral 12B 2409 hf text only support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Pixtral 12B 2409 hf text only GGUF?
The files are on Hugging Face in the leafspark/Pixtral-12B-2409-hf-text-only-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 Pixtral 12B 2409 hf text only use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.