estimate, except measured file sizes
Can I run Qwen2.5 72B locally?
72.7B parameters. Parameter count is an estimate.
- Licence:
- not recorded
- Context:
- 131,072 tokens
- Modality:
- not recorded
- Released:
- not recorded
Same class as Llama 70B. A bartowski Qwen2.5-72B-Instruct Q4_K_M file is 47.42 GB (47,415,715,488 bytes), larger than 72.7 × 0.60. IQ4_XS from the same repo is 39.71 GB. You need a large memory pool.
· Architecture source · Model page
Memory per quant
KV is at 8,192 tokens. Overhead is 0.8 GB. Both are estimates. A measured file size is labelled. The last column is the cheapest machine that fits the total fully.
| Quant | File size | KV at 8K | +0.8 overhead | Total | Cheapest full fit |
|---|---|---|---|---|---|
| Q8 | 77.8 GB est. | 2.7 GB est. | 0.8 GB est. | 81.3 GB est. | Mac Studio M4 Max 128GB, €3,290 (estimate) |
| Q4 | 47.4 GB measured GGUF | 2.7 GB est. | 0.8 GB est. | 50.9 GB est. | Mac mini M4 Pro 64GB, €1,890 (estimate) |
Cheapest rig that fits
Q4, full: Mac mini M4 Pro 64GB, €1,890 (estimate)
Q4, slow, partly in system RAM: Budget PC with RTX 3060 12GB, slow, partly in system RAM, €1,357 (estimate)