Qwen2.5-72B
Qwen2.5-72B is an open-weights language model from Qwen, released September 19, 2024. It has 73B parameters (dense). The context window is 128K tokens. On the Epoch Capabilities Index it scores 127.2, rank 165 of 256 rated models.
Check it against your own PC →
Can you run Qwen2.5-72B locally?
The smallest common GPU it runs on is 24 GB of VRAM (with 32 GB of RAM): IQ2_XXS, split GPU / CPU, roughly 12 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 7.2 GB | 17.5 GB | ~2 |
| 12 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 11.2 GB | 13.5 GB | ~2 |
| 16 GB VRAM | Very slow | IQ2_XXS (heavy loss) | 15.2 GB | 9.5 GB | ~3 |
| 24 GB VRAM | Runs, slowly | IQ2_XXS (heavy loss) | 23.2 GB | 1.5 GB | ~12 |
| 32 GB VRAM | Runs on GPU | IQ2_M (heavy loss) | 30.5 GB | – | ~42 |
Ready-made quantizations on Hugging Face: ThomasBaruzier/Qwen2.5-72B-Instruct-GGUF · mradermacher/Qwen2.5-72B-i1-GGUF · mradermacher/Qwen2.5-72B-GGUF · zetasepic/Qwen2.5-72B-Instruct-abliterated-v2-GGUF · featherless-ai-quants/Qwen-Qwen2.5-72B-GGUF · billatsectorflow/Qwen2.5-72B-Instruct-GPTQ-Int4-128K
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 15.7 | MATH level 5, OTIS Mock AIME 2024-2025 |
| Agent | 10.2 | Balrog, The Agent Company, OSWorld |
| Knowledge | 34.8 | GPQA diamond, MMLU |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 80.4% |
| MATH level 5 | 63.2% |
| GPQA Diamond | 33.5% |
| Balrog | 16.2% |
| OTIS Mock AIME | 8.0% |
| The Agent Company | 5.7% |
| OSWorld | 5.0% |
Links
Hugging Face: Qwen/Qwen2.5-72B · Epoch AI benchmarks
Models with a similar score
Qwen2.5-Max · Gemini 1.5 Pro (Sept 2024) · Claude 3.5 Sonnet · Grok-2 (Dec 2024) · Phi-4 · GPT-4o (Nov 2024) · GPT-4o (May 2024) · Llama 3.1-405B
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash