Trinity 2 Codestral 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 20 quants, from 7.6 GB (IQ2_M) to 89.0 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
Trinity 2 Codestral 22B – a 22.2B coding‑focused LLM
Trinity 2 Codestral 22B is a 22.2B parameter model built on the Mistral family and llama architecture. It is optimized for code generation and supports a 32768 token context window. The model is available in multiple GGUF quantizations.
Good at
- Code generation
- Large context handling
- LLM inference with llama.cpp
Limits
- No vision support
- License is other
- Requires significant VRAM for higher quants
Best for
- Developers writing code
- Educational coding tools
- Automated code review
Who it’s for. Engineers and researchers who need a large, code‑centric language model that can run locally with llama.cpp. The model is suitable for users with GPU memory to accommodate the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| 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_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 → | |
| F32 | 89.0 GB (3 parts) | 91.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 13.34 GB, memory 15.7 GB). For 12 GB VRAM, Q4_K_L (13.49 GB, 15.9 GB). For 16 GB VRAM, Q5_K_M (15.72 GB, 18.1 GB). Memory estimates are approximate.
What GPU do you need for Trinity 2 Codestral 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 Q8_0 (23.6 GB file, about 26.0 GB in use).
Which Trinity 2 Codestral 22B quant should you choose?
Q4_K_M is the usual starting point for Trinity 2 Codestral 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_M at 7.6 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 Trinity 2 Codestral 22B
How much VRAM does Trinity 2 Codestral 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 Trinity 2 Codestral 22B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Trinity 2 Codestral 22B GGUF?
It depends on the quant: 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, Q3_K_S is 9.6 GB, IQ3_M is 10.1 GB and 14 more.
What context length does Trinity 2 Codestral 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 Trinity 2 Codestral 22B GGUF?
The files are on Hugging Face in the bartowski/Trinity-2-Codestral-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 Trinity 2 Codestral 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 Trinity 2 Codestral 22B on 8 GB VRAM?
Use the Q4_K_M quant, which requires about 15.7 GB of VRAM at 8 k context. It will not fit fully in 8 GB VRAM, so you need more memory or a smaller quant.
What is the largest quant I can use on a 24 GB GPU?
The Q8_0 quant is 23.64 GB and needs about 26 GB of VRAM. It will not fit on 24 GB VRAM; consider Q6_K (18.25 GB, 20.6 GB) instead.
Does the model support image inputs?
No, the model has no vision capabilities and only supports text input.