Compare
Compare models side by side
Choose up to 4 models to see their file size, memory, license and third-party evaluations side by side.
Comparison table
| Item | Qwen2.5-72B-Instruct Qwen ✕ Remove |
|---|---|
| Parameters | 72.7B |
| Architecture | qwen2 |
| Max context length | 32,768 |
| Representative quantization and size Measured | Q4_K_M · 47.4 GB |
| Memory at 8K Estimated | 50.9 GB |
| Memory at 32K Estimated | 59.0 GB |
| VRAM it fits (8K) Estimated | VRAM 48 GB+ |
| Smallest quantization (8K) Estimated | IQ1_M · 23.7 GB → 27.3 GB |
| License | Qwen License Agreement Conditional |
| llama.cpp support | Supported before llama.cpp b4409 |
| Downloads (30 days, total) | 57,732 |
| Human preference (LMArena) | 1,303 qwen2.5-72b-instruct |
| Capabilities (Epoch AI) | - |
| Hard science (GPQA) | 49.1% qwen2.5-72b-instruct |
- The representative quantization is Q4_K_M (or the smallest one if missing) from the source with the most downloads. Memory is estimated with an f16 KV cache.
- Third-party evaluations are other organizations' values for the original model before quantization, not this site's rating (sources are on the ranking page).
- This site does not judge which model is better or give an overall score.