magnum v2 32b needs about 25.7 GB of memory at Q5_K (a 23.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 5 quants, from 14.7 GB (IQ3_M) to 34.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
magnum v2 32b is a 32.5B-parameter Magnum model in GGUF format, quantized by anthracite-org. Its trained context length is 32K tokens. The repository has 5 quant files, from 14.7 GB (IQ3_M) to 34.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 14.7 GB | 17.3 GB | Too big | Get file → | |
| Q4_K | 19.7 GB | 22.3 GB | Too big | Get file → | |
| Q5_K | 23.1 GB | 25.7 GB | Too big | Get file → | |
| Q6_K | 26.7 GB | 29.3 GB | Too big | Get file → | |
| Q8_0 | 34.6 GB | 37.2 GB | Too big | Get file → |
What GPU do you need for magnum v2 32b?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K (19.7 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 29.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.6 GB file, about 37.2 GB in use).
Which magnum v2 32b quant should you choose?
Q5_K (23.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is IQ3_M at 14.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about magnum v2 32b
How much VRAM does magnum v2 32b need?
About 25.7 GB at Q5_K with an 8K context window. That is the 23.1 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 magnum v2 32b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of magnum v2 32b GGUF?
It depends on the quant: IQ3_M is 14.7 GB, Q4_K is 19.7 GB, Q5_K is 23.1 GB, Q6_K is 26.7 GB, Q8_0 is 34.6 GB.
What context length does magnum v2 32b support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download magnum v2 32b GGUF?
The files are on Hugging Face in the anthracite-org/magnum-v2-32b-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 magnum v2 32b 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.