magnum v4 123b heretic DE needs about 76.7 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 73.2 GB (Q4_K_M) to 245.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.
magnum v4 123b heretic DE is a 123B-parameter Magnum model in GGUF format, quantized by Frisch12. Its trained context length is 128K tokens. The repository has 5 quant files, from 73.2 GB (Q4_K_M) to 245.2 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 73.2 GB (3 parts) | 76.7 GB | Too big | Get file → | |
| Q5_K_M | 86.5 GB (3 parts) | 89.9 GB | Too big | Get file → | |
| Q6_K | 100.6 GB (4 parts) | 104.0 GB | Too big | Get file → | |
| Q8_0 | 130.3 GB (5 parts) | 133.7 GB | Too big | Get file → | |
| F16 | 245.2 GB (8 parts) | 248.7 GB | Too big | Get file → |
What GPU do you need for magnum v4 123b heretic DE?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which magnum v4 123b heretic DE quant should you choose?
Q4_K_M is the usual starting point for magnum v4 123b heretic DE: it balances file size and quality well. Here it is a 73.2 GB file.
The Q8_0 file is 130.3 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about magnum v4 123b heretic DE
How much VRAM does magnum v4 123b heretic DE need?
About 76.7 GB at Q4_K_M with an 8K context window. That is the 73.2 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 v4 123b heretic DE on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 76.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of magnum v4 123b heretic DE GGUF?
It depends on the quant: Q4_K_M is 73.2 GB, Q5_K_M is 86.5 GB, Q6_K is 100.6 GB, Q8_0 is 130.3 GB, F16 is 245.2 GB.
What context length does magnum v4 123b heretic DE support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.
Where can I download magnum v4 123b heretic DE GGUF?
The files are on Hugging Face in the Frisch12/magnum-v4-123b-heretic-DE-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 v4 123b heretic DE 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.