Qwen2.5
Qwen2.5-72B-Instruct
Alibaba (Qwen team) · open-restricted qwen
| Parameters (B) | 72.706 |
|---|---|
| Architecture | dense |
| Layers / KV heads / head dim | 80 / 8 / 128 |
| Context window | 32768 |
| Modalities | in: text; out: text |
| GGUF | available |
| Commercial use | yes |
Minimum hardware (estimate)
At Q4_K_M and 8k context, total working set ≈ 47.4 GiB. On a machine with 64 GiB system RAM and no discrete GPU: Won't run. Limiting factor: No GPU and system RAM insufficient for weights + KV.
Scores
| Benchmark | Value | Uncertainty | Run by | Source |
|---|---|---|---|---|
| GPQA Diamond | 49.1% | unknown | third-party | epoch-ai |
| MATH Level 5 | 63.2% | unknown | third-party | epoch-ai |
| OTIS Mock AIME 2024-2025 | 8.1% | unknown | third-party | epoch-ai |
Provenance
- identity, license, architecture, parameter count: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct (retrieved 2026-08-10)
HF: Qwen/Qwen2.5-72B-Instruct · snapshot 2026-08-10