M3.2 24B Loki V1.3 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 27 quants, from 0.0 GB to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
M3.2 24B Loki V1.3 – a 23.6B parameter Llama model
M3.2 24B Loki V1.3 is a 23.6B parameter Llama model with a 131072 token context window. It is released under the apache-2.0 license and supports a wide range of quantizations for different memory budgets.
Good at
- Large context handling
- High parameter count
- Flexible quantization options
Limits
- No vision support
- Requires 8k context for memory estimates
- License is apache-2.0
Best for
- Long‑form content generation
- Research prototyping
- Fine‑tuning on custom datasets
Who it’s for. Developers and researchers who need a large Llama model with a long context window and who can manage the memory requirements. The model is suitable for those who prefer open‑source licensing and are comfortable with llama.cpp or similar runtimes.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.9 GB | Fits | Get file → | |
| IQ2_XS | 7.2 GB | 9.0 GB | Too big | Get file → | |
| IQ2_S | 7.5 GB | 9.3 GB | Too big | Get file → | |
| IQ2_M | 8.1 GB | 10.0 GB | Too big | Get file → | |
| Q2_K | 8.9 GB | 10.7 GB | Too big | Get file → | |
| IQ3_XXS | 9.3 GB | 11.1 GB | Too big | Get file → | |
| Q2_K_L | 9.5 GB | 11.4 GB | Too big | Get file → | |
| IQ3_XS | 9.9 GB | 11.7 GB | Too big | Get file → | |
| Q3_K_S | 10.4 GB | 12.2 GB | Too big | Get file → | |
| IQ3_M | 10.7 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_M | 11.5 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_L | 12.4 GB | 14.2 GB | Too big | Get file → | |
| IQ4_XS | 12.8 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_XL | 13.0 GB | 14.8 GB | Too big | Get file → | |
| IQ4_NL | 13.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_0 | 13.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_K_S | 13.5 GB | 15.4 GB | Too big | Get file → | |
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_L | 14.8 GB | 16.7 GB | Too big | Get file → | |
| Q4_1 | 14.9 GB | 16.7 GB | Too big | Get file → | |
| Q5_K_S | 16.3 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_M | 16.8 GB | 18.6 GB | Too big | Get file → | |
| Q5_K_L | 17.2 GB | 19.0 GB | Too big | Get file → | |
| Q6_K | 19.3 GB | 21.2 GB | Too big | Get file → | |
| Q6_K_L | 19.7 GB | 21.5 GB | Too big | Get file → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → | |
| BF16 | 47.2 GB | 49.0 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ2_XS (7.21 GB file, 9 GB memory at 8k context). For 16‑GB VRAM, Q4_K_M (14.33 GB file, 16.2 GB memory) or Q5_K_S (16.3 GB file, 18.1 GB memory). For 32‑GB VRAM, Q6_K (19.35 GB file, 21.2 GB memory) or Q8_0 (25.05 GB file, 26.9 GB memory).
What GPU do you need for M3.2 24B Loki V1.3?
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: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (9.9 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (13.5 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_L (19.7 GB file, about 21.5 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 Q8_0 (25.1 GB file, about 26.9 GB in use).
Which M3.2 24B Loki V1.3 quant should you choose?
Q4_K_M is the usual starting point for M3.2 24B Loki V1.3: 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about M3.2 24B Loki V1.3
How much VRAM does M3.2 24B Loki V1.3 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 M3.2 24B Loki V1.3 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of M3.2 24B Loki V1.3 GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XS is 7.2 GB, IQ2_S is 7.5 GB, IQ2_M is 8.1 GB, Q2_K is 8.9 GB, IQ3_XXS is 9.3 GB and 21 more.
What context length does M3.2 24B Loki V1.3 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 M3.2 24B Loki V1.3 GGUF?
The files are on Hugging Face in the bartowski/CrucibleLab_M3.2-24B-Loki-V1.3-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 M3.2 24B Loki V1.3 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 M3.2 24B Loki V1.3 on 8 GB VRAM?
Use the IQ2_XS quantization; it requires about 9 GB of VRAM at 8k context, which is close to 8 GB but may need a small batch size.
Does the model support vision tasks?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.