Codestral-22B-v0.1-abliterated-v3 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 21 quants, from 4.8 GB (IQ1_S) to 18.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
22B-code model with refusal orthogonalized
Codestral-22B-v0.1-abliterated-v3 is a 22.2B parameter code model based on Mistral architecture. It has been orthogonalized to reduce refusal behaviour while maintaining original coding performance. The model supports a 32768 token context window.
Good at
- coding tasks
- code generation
- code debugging
Limits
- no vision support
- no explicit license details
- no refusal guarantee
Best for
- writing scripts
- auto‑completion in IDEs
- generating code snippets
Who it’s for. Developers and researchers needing a large code model with minimal refusal. Suitable for local deployment on machines with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.8 GB | 7.2 GB | Tight | Get file → | |
| IQ1_M | 5.3 GB | 7.6 GB | Tight | Get file → | |
| IQ2_XXS | 6.0 GB | 8.4 GB | Too big | Get file → | |
| 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 → | |
| IQ3_XXS | 8.6 GB | 11.0 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_S | 9.7 GB | 12.1 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 → | |
| IQ4_XS | 11.9 GB | 14.3 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 → | |
| 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 → | |
| Q6_K | 18.3 GB | 20.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.83 GB, 7.2 GB memory at 8k context). For 12 GB VRAM, IQ2_XS (6.65 GB, 9 GB memory) or Q2_K (8.27 GB, 10.7 GB memory). For 24 GB VRAM, Q4_K_M (13.34 GB, 15.7 GB memory) offers a good balance of size and performance.
What GPU do you need for Codestral-22B-v0.1-abliterated-v3?
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 IQ1_M (5.3 GB file, about 7.6 GB in use).
- 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_M (13.3 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).
Which Codestral-22B-v0.1-abliterated-v3 quant should you choose?
Q4_K_M is the usual starting point for Codestral-22B-v0.1-abliterated-v3: it balances file size and quality well. Here it is a 13.3 GB file.
If memory is tight, the smallest file is IQ1_S at 4.8 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
Frequently asked questions about Codestral-22B-v0.1-abliterated-v3
How much VRAM does Codestral-22B-v0.1-abliterated-v3 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 Codestral-22B-v0.1-abliterated-v3 on an 8 GB GPU?
Yes, with IQ1_M: the 5.3 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 Codestral-22B-v0.1-abliterated-v3 GGUF?
It depends on the quant: IQ1_S is 4.8 GB, IQ1_M is 5.3 GB, IQ2_XXS is 6.0 GB, IQ2_XS is 6.6 GB, IQ2_S is 7.0 GB, IQ2_M is 7.6 GB and 15 more.
What context length does Codestral-22B-v0.1-abliterated-v3 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 Codestral-22B-v0.1-abliterated-v3 GGUF?
The files are on Hugging Face in the mradermacher/Codestral-22B-v0.1-abliterated-v3-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, the IQ1_S quant requires 4.83 GB file size and estimates 7.2 GB VRAM at 8k context.
Does this model refuse to answer?
The refusal behaviour has been orthogonalized, but no guarantee of no refusal exists.
What is the context length?
The model supports 32768 tokens of context.