Will this model run on your hardware?
Can I run Magnum v4 72B locally?
- 73B parameters
- context up to 32K
- licence: apache-2.0
- Weights: anthracite-org/magnum-v4-72b · GGUF: bartowski/magnum-v4-72b-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 77.3 GB |
| Q6_K | 64.3 GB |
| Q5_K_M | 54.4 GB |
| Q4_K_M | 47.4 GB |
| Q3_K_M | 37.7 GB |
| Q2_K | 29.8 GB |
Run it locally
ollama run hf.co/bartowski/magnum-v4-72b-GGUF:Q4_K_M
llama serve -hf bartowski/magnum-v4-72b-GGUF:Q4_K_M
LM Studio: open bartowski/magnum-v4-72b-GGUF