Mistral Small Drummer 22B needs about 15.7 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 26 quants, from 6.6 GB (IQ2_XS) to 44.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
Mistral Small Drummer 22B – 22.2B llama architecture model
Mistral Small Drummer 22B is a 22.2B parameter llama model fine‑tuned with ORPO on a Gutenberg DPO dataset. It supports a 32768 token context window and is available in multiple GGUF quantizations. The model is released under an other license with no specified prompt format.
Good at
- Large context handling
- Fine‑tuned on DPO data
- Available in many quantizations
Limits
- No vision support
- License not specified for commercial use
- No prompt format provided
Best for
- Long‑form text generation
- Fine‑tuned instruction following
- Running on GPUs with sufficient VRAM
Who it’s for. Developers and researchers who need a large llama model with extended context and multiple quantization options. Suitable for those who can manage the memory requirements and are comfortable with a model that has no explicit prompt format.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 6.6 GB | 9.0 GB | Too big | Get file → | |
| IQ2_S | 7.0 GB | 9.4 GB | Too big | Get file → | |
| IQ2_M | 7.6 GB | 10.0 GB | Too big | Get file → | |
| Q2_K | 8.3 GB | 10.7 GB | Too big | Get file → | |
| Q2_K_L | 8.5 GB | 10.8 GB | Too big | Get file → | |
| IQ3_XS | 9.2 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_S | 9.6 GB | 12.0 GB | Too big | Get file → | |
| IQ3_M | 10.1 GB | 12.4 GB | Too big | Get file → | |
| Q3_K_M | 10.8 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_L | 11.7 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_XL | 11.9 GB | 14.3 GB | Too big | Get file → | |
| IQ4_XS | 11.9 GB | 14.3 GB | Too big | Get file → | |
| Q4_0 | 12.6 GB | 14.9 GB | Too big | Get file → | |
| Q4_0 | 12.6 GB | 14.9 GB | Too big | Get file → | |
| Q4_0 | 12.6 GB | 14.9 GB | Too big | Get file → | |
| Q4_0 | 12.6 GB | 15.0 GB | Too big | Get file → | |
| Q4_K_S | 12.7 GB | 15.0 GB | Too big | Get file → | |
| Q4_K_M | 13.3 GB | 15.7 GB | Too big | Get file → | |
| Q4_K_L | 13.5 GB | 15.9 GB | Too big | Get file → | |
| Q5_K_S | 15.3 GB | 17.7 GB | Too big | Get file → | |
| Q5_K_M | 15.7 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_L | 15.8 GB | 18.2 GB | Too big | Get file → | |
| Q6_K | 18.3 GB | 20.6 GB | Too big | Get file → | |
| Q6_K_L | 18.4 GB | 20.7 GB | Too big | Get file → | |
| Q8_0 | 23.6 GB | 26.0 GB | Too big | Get file → | |
| F16 | 44.5 GB | 46.9 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ2_XS (file size 6.65 GB, estimated 9 GB memory). For 12‑GB VRAM, Q4_K_S (12.66 GB, 15 GB memory) or Q4_K_M (13.34 GB, 15.7 GB memory). For 24‑GB VRAM, Q8_0 (23.64 GB, 26 GB memory) provides the highest quality. Estimates are approximate.
What GPU do you need for Mistral Small Drummer 22B?
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 Q3_K_S (9.6 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_L (13.5 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_L (18.4 GB file, about 20.7 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (23.6 GB file, about 26.0 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (44.5 GB file, about 46.9 GB in use).
Which Mistral Small Drummer 22B quant should you choose?
Q4_K_M is the usual starting point for Mistral Small Drummer 22B: it balances file size and quality well. Here it is a 13.3 GB file.
The Q8_0 file is 23.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ2_XS at 6.6 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
Source
Frequently asked questions about Mistral Small Drummer 22B
How much VRAM does Mistral Small Drummer 22B need?
About 15.7 GB at Q4_K_M with an 8K context window. That is the 13.3 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 Mistral Small Drummer 22B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Mistral Small Drummer 22B GGUF?
It depends on the quant: IQ2_XS is 6.6 GB, IQ2_S is 7.0 GB, IQ2_M is 7.6 GB, Q2_K is 8.3 GB, Q2_K_L is 8.5 GB, IQ3_XS is 9.2 GB and 20 more.
What context length does Mistral Small Drummer 22B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.
Where can I download Mistral Small Drummer 22B GGUF?
The files are on Hugging Face in the bartowski/Mistral-Small-Drummer-22B-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 Mistral Small Drummer 22B 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 Mistral Small Drummer 22B on 8 GB VRAM?
Yes, using the IQ2_XS quantization (6.65 GB file, ~9 GB memory at 8k context).
Does this model support image inputs?
No, the model has no vision capabilities. It is purely text‑based.
What license does the model use?
The model is released under an other license; check the repository for specific terms.