Magistral-Small-2506-abliterated needs about 16.2 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 31 quants, from 5.6 GB (TQ1_0) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Magistral‑Small‑2506‑abliterated – a 23.6B reasoning‑focused LLM
Magistral‑Small‑2506‑abliterated is a 23.6B parameter model built on Mistral architecture. It adds reasoning capabilities and supports a 128k context window, though performance is best below 40k tokens. The model is released under Apache‑2.0 and can be run locally with quantization.
Good at
- Long‑chain reasoning
- Large context handling
- Multilingual support
Limits
- Requires quantization for local use
- Performance degrades past 40k tokens
- No vision support
Best for
- Chatbots needing reasoning
- Document summarisation with long context
- Multilingual QA
Who it’s for. Developers and researchers who need a small, efficient reasoning model that can run on consumer GPUs or laptops after quantization. The Apache‑2.0 license allows commercial use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 5.6 GB | 7.5 GB | Tight | Get file → | |
| IQ1_S | 6.5 GB | 8.4 GB | Too big | Get file → | |
| TQ2_0 | 6.7 GB | 8.5 GB | Too big | Get file → | |
| IQ1_M | 7.0 GB | 8.9 GB | Too big | Get file → | |
| IQ2_XXS | 7.4 GB | 9.2 GB | Too big | Get file → | |
| IQ2_XS | 8.0 GB | 9.8 GB | Too big | Get file → | |
| IQ2_S | 8.2 GB | 10.1 GB | Too big | Get file → | |
| Q2_K_S | 8.4 GB | 10.2 GB | Too big | Get file → | |
| IQ2_M | 8.7 GB | 10.5 GB | Too big | Get file → | |
| Q2_K_M | 9.1 GB | 11.0 GB | Too big | Get file → | |
| IQ3_XXS | 9.5 GB | 11.4 GB | Too big | Get file → | |
| IQ3_XS | 10.0 GB | 11.8 GB | Too big | Get file → | |
| IQ3_S | 10.5 GB | 12.3 GB | Too big | Get file → | |
| IQ3_M | 10.6 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_S | 10.6 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_M | 11.6 GB | 13.5 GB | Too big | Get file → | |
| IQ4_XS | 12.8 GB | 14.6 GB | Too big | Get file → | |
| Q4_0 | 13.3 GB | 15.1 GB | Too big | Get file → | |
| IQ4_NL | 13.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_K_S | 13.8 GB | 15.7 GB | Too big | Get file → | |
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → | |
| Q4_1 | 14.7 GB | 16.6 GB | Too big | Get file → | |
| Q5_0 | 16.2 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_S | 16.6 GB | 18.4 GB | Too big | Get file → | |
| Q5_K_M | 16.9 GB | 18.7 GB | Too big | Get file → | |
| Q5_1 | 17.7 GB | 19.5 GB | Too big | Get file → | |
| Q6_K_M | 19.3 GB | 21.2 GB | Too big | Get file → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → | |
| BF16 | 33.6 GB | 35.4 GB | Too big | Get file → | |
| F16 | 33.6 GB | 35.4 GB | Too big | Get file → | |
| BF16 | 47.2 GB | 49.0 GB | Too big | Get file → |
For 8‑GB VRAM, use TQ1_0 (file size 5.63 GB, estimated 7.5 GB memory at 8k context). For 12‑GB VRAM, IQ1_S (6.52 GB, 8.4 GB) or TQ2_0 (6.67 GB, 8.5 GB). For 16‑GB VRAM, Q4_K_M (14.34 GB, 16.2 GB) or Q5_K_M (16.88 GB, 18.7 GB). Estimates are approximate.
What GPU do you need for Magistral-Small-2506-abliterated?
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: the best quant that fits is TQ1_0 (5.6 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (10.0 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (13.8 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_M (19.3 GB file, about 21.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (33.6 GB file, about 35.4 GB in use).
Which Magistral-Small-2506-abliterated quant should you choose?
Q4_K_M is the usual starting point for Magistral-Small-2506-abliterated: it balances file size and quality well. Here it is a 14.3 GB file.
The Q8_0 file is 25.1 GB, about 1.7 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 TQ1_0 at 5.6 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Magistral-Small-2506-abliterated
How much VRAM does Magistral-Small-2506-abliterated need?
About 16.2 GB at Q4_K_M 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 Magistral-Small-2506-abliterated on an 8 GB GPU?
Yes, with TQ1_0: the 5.6 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Magistral-Small-2506-abliterated GGUF?
It depends on the quant: TQ1_0 is 5.6 GB, IQ1_S is 6.5 GB, TQ2_0 is 6.7 GB, IQ1_M is 7.0 GB, IQ2_XXS is 7.4 GB, IQ2_XS is 8.0 GB and 25 more.
What context length does Magistral-Small-2506-abliterated support?
The GGUF header lists a trained context length of 40,960 tokens (40K). 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 Magistral-Small-2506-abliterated GGUF?
The files are on Hugging Face in the Mungert/Magistral-Small-2506-abliterated-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 Magistral-Small-2506-abliterated 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.
Can I run Magistral‑Small‑2506‑abliterated on an RTX 4090 with 8 GB VRAM?
The smallest quant, TQ1_0, requires about 7.5 GB memory at 8k context, so it fits on 8 GB VRAM but may be tight for larger contexts.
What is the maximum context length I should use?
The model supports up to 128k tokens, but performance is best when the maximum length is set to 40k tokens.
Is the model licensed for commercial use?
Yes, it is released under the Apache‑2.0 license, which permits commercial and non‑commercial use.