Loading…
Loading…
Models / Qwen2.5
7 models (0.5B to 72B) · ↓ 45.2M downloads a month · from $0.08/h on GTX 1660 SUPER right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen2.5-0.5B | vLLM | 990 MB | 3.4 GB | $0.10/h RTX 3060 |
| InstructQwen/Qwen2.5-0.5B-Instruct | vLLM | 990 MB | 3.4 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 0.5B InstructQwen/Qwen2.5-Coder-0.5B-Instruct | vLLM | 990 MB | 3.4 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 0.5BQwen/Qwen2.5-Coder-0.5B | vLLM | 990 MB | 3.4 GB | $0.10/h RTX 3060 |
| Instruct AWQQwen/Qwen2.5-0.5B-Instruct-AWQ | vLLM | 730 MB | 3.1 GB | $0.10/h RTX 3060 |
| turn detector (livekit)livekit/turn-detector | ONNX Runtime | 170 MB | 1.2 GB | $0.08/h GTX 1660 SUPER |
| Instruct (onnx-community)onnx-community/Qwen2.5-0.5B-Instruct | ONNX Runtime | 480 MB | 1.7 GB | $0.08/h GTX 1660 SUPER |
| Instruct unsloth bnb 4bit (unsloth)unsloth/Qwen2.5-0.5B-Instruct-unsloth-bnb-4bit | vLLM | 540 MB | 2.9 GB | $0.10/h RTX 3060 |
| Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit | vLLM | 460 MB | 2.8 GB | $0.10/h RTX 3060 |
| unsloth bnb 4bit (unsloth)unsloth/Qwen2.5-0.5B-unsloth-bnb-4bit | vLLM | 520 MB | 2.9 GB | $0.10/h RTX 3060 |
| Instruct onnx genai (xiaoyao9184)xiaoyao9184/Qwen2.5-0.5B-Instruct-onnx-genai | ONNX Runtime GenAI | 550 MB | 2.2 GB | $0.08/h GTX 1660 SUPER |
| LocalLLMs ToolCalling (elbruno)elbruno/Qwen2.5-0.5B-LocalLLMs-ToolCalling | ONNX Runtime GenAI | 880 MB | 2.6 GB | $0.08/h GTX 1660 SUPER |
| Instruct onnx genai (techierathore)techierathore/Qwen2.5-0.5B-Instruct-onnx-genai | ONNX Runtime GenAI | 330 MB | 2 GB | $0.08/h GTX 1660 SUPER |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen2.5-1.5B | vLLM | 3.1 GB | 5.9 GB | $0.10/h RTX 3060 |
| InstructQwen/Qwen2.5-1.5B-Instruct | vLLM | 3.1 GB | 5.9 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 1.5B InstructQwen/Qwen2.5-Coder-1.5B-Instruct | vLLM | 3.1 GB | 5.9 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 1.5BQwen/Qwen2.5-Coder-1.5B | vLLM | 3.1 GB | 5.9 GB | $0.10/h RTX 3060 |
| Qwen2.5 Math 1.5BQwen/Qwen2.5-Math-1.5B | vLLM | 3.1 GB | 5.8 GB | $0.10/h RTX 3060 |
| Qwen2.5 Math 1.5B InstructQwen/Qwen2.5-Math-1.5B-Instruct | vLLM | 3.1 GB | 5.8 GB | $0.10/h RTX 3060 |
| Instruct AWQQwen/Qwen2.5-1.5B-Instruct-AWQ |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen2.5-3B | vLLM | 6.2 GB | 9.4 GB | $0.10/h RTX 3060 |
| InstructQwen/Qwen2.5-3B-Instruct | vLLM | 6.2 GB | 9.4 GB | $0.10/h RTX 3060 |
| Instruct AWQQwen/Qwen2.5-3B-Instruct-AWQ | vLLM | 2.7 GB | 5.5 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 3B InstructQwen/Qwen2.5-Coder-3B-Instruct | vLLM | 6.2 GB | 9.4 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 3BQwen/Qwen2.5-Coder-3B | vLLM | 6.2 GB | 9.4 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 3B Instruct AWQQwen/Qwen2.5-Coder-3B-Instruct-AWQ | vLLM | 2.7 GB | 5.5 GB | $0.10/h RTX 3060 |
| Instruct unsloth bnb 4bit (unsloth) |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen2.5-7B | vLLM | 15 GB | 19.7 GB | $0.18/h 2x RTX 3060 |
| InstructQwen/Qwen2.5-7B-Instruct | vLLM | 15 GB | 19.7 GB | $0.18/h 2x RTX 3060 |
| Instruct AWQQwen/Qwen2.5-7B-Instruct-AWQ | vLLM | 5.6 GB | 8.9 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 7B InstructQwen/Qwen2.5-Coder-7B-Instruct | vLLM | 15 GB | 19.7 GB | $0.18/h 2x RTX 3060 |
| Qwen2.5 Coder 7B Instruct AWQQwen/Qwen2.5-Coder-7B-Instruct-AWQ | vLLM | 5.6 GB | 8.9 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 7B Instruct GPTQ Int4Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 | vLLM | 5.6 GB | 8.9 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen2.5-14B | vLLM | 30 GB | 36.8 GB | $0.45/h Nvidia A40 |
| Instruct AWQQwen/Qwen2.5-14B-Instruct-AWQ | vLLM | 10.0 GB | 15.1 GB | $0.14/h RTX A4000 |
| InstructQwen/Qwen2.5-14B-Instruct | vLLM | 30 GB | 36.8 GB | $0.45/h Nvidia A40 |
| Instruct GPTQ Int4Qwen/Qwen2.5-14B-Instruct-GPTQ-Int4 | vLLM | 10.0 GB | 15.1 GB | $0.14/h RTX A4000 |
| Instruct 1MQwen/Qwen2.5-14B-Instruct-1M | vLLM | 30 GB | 36.8 GB | $0.45/h Nvidia A40 |
| bnb 4bit (unsloth)unsloth/Qwen2.5-14B-bnb-4bit | vLLM | 9.9 GB | 15 GB | $0.14/h RTX A4000 |
| Instruct bnb 4bit (unsloth) |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen2.5-32B | vLLM | 66 GB | 77.4 GB | $0.89/h 2x Nvidia A40 |
| InstructQwen/Qwen2.5-32B-Instruct | vLLM | 66 GB | 77.4 GB | $0.89/h 2x Nvidia A40 |
| Instruct AWQQwen/Qwen2.5-32B-Instruct-AWQ | vLLM | 19 GB | 26.1 GB | $0.34/h 2x RTX 5060 Ti |
| Qwen2.5 Coder 32B Instruct AWQQwen/Qwen2.5-Coder-32B-Instruct-AWQ | vLLM | 19 GB | 26.1 GB | $0.34/h 2x RTX 5060 Ti |
| Qwen2.5 Coder 32B InstructQwen/Qwen2.5-Coder-32B-Instruct | vLLM | 66 GB | 77.4 GB | $0.89/h 2x Nvidia A40 |
| Instruct GPTQ Int4Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4 | vLLM | 19 GB | 26.1 GB | $0.34/h 2x RTX 5060 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalQwen/Qwen2.5-72B | vLLM | 145 GB | 166.8 GB | $1.38/h 8x RTX 3090 |
| Instruct AWQQwen/Qwen2.5-72B-Instruct-AWQ | vLLM | 42 GB | 51.4 GB | $0.78/h 4x RTX 4060 Ti |
| InstructQwen/Qwen2.5-72B-Instruct | vLLM | 145 GB | 166.8 GB | $1.38/h 8x RTX 3090 |
| Instruct GPTQ Int4Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4 | vLLM | 42 GB | 51.5 GB | $0.78/h 4x RTX 4060 Ti |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").
| vLLM |
| 1.6 GB |
| 4.3 GB |
| $0.10/h RTX 3060 |
| quantized.w8a8 (RedHatAI)RedHatAI/Qwen2.5-1.5B-quantized.w8a8 | vLLM | 2.3 GB | 5 GB | $0.10/h RTX 3060 |
| Instruct unsloth bnb 4bit (unsloth)unsloth/Qwen2.5-1.5B-Instruct-unsloth-bnb-4bit | vLLM | 1.5 GB | 4.2 GB | $0.10/h RTX 3060 |
| unsloth bnb 4bit (unsloth)unsloth/Qwen2.5-1.5B-unsloth-bnb-4bit | vLLM | 1.4 GB | 4 GB | $0.10/h RTX 3060 |
| Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit | vLLM | 1.1 GB | 3.8 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 1.5B Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit | vLLM | 1.1 GB | 3.8 GB | $0.10/h RTX 3060 |
| Instruct (onnx-community)onnx-community/Qwen2.5-1.5B-Instruct | ONNX Runtime | 1.2 GB | 2.8 GB | $0.08/h GTX 1660 SUPER |
| qwen2 5 1 5b instruct onnx genai int4 kquantlast emb int4 (Arm)Arm/qwen2-5-1-5b-instruct-onnx-genai-int4-kquantlast-emb-int4 | ONNX Runtime GenAI | 1.1 GB | 3 GB | $0.08/h GTX 1660 SUPER |
| Instruct ONNX (tonythethompson)tonythethompson/Qwen2.5-1.5B-Instruct-ONNX | ONNX Runtime GenAI | 6.2 GB | 8.9 GB | $0.09/h RTX 3060 |
| qwen2.5 coder text2sql onnx (spcv)spcv/qwen2.5_coder_text2sql_onnx | ONNX Runtime GenAI | 1.0 GB | 2.9 GB | $0.08/h GTX 1660 SUPER |
| vLLM |
| 2.4 GB |
| 5.2 GB |
| $0.10/h RTX 3060 |
| Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-3B-Instruct-bnb-4bit | vLLM | 2.0 GB | 4.8 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 3B Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit | vLLM | 2.0 GB | 4.8 GB | $0.10/h RTX 3060 |
| qwen2.5 coder 3b claude opus 4.6 distilled (ryzdfm)ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled | vLLM | 6.2 GB | 9.4 GB | $0.10/h RTX 3060 |
| opnsense qwen25 onnx int4 (patlegu)patlegu/opnsense-qwen25-onnx-int4 | ONNX Runtime GenAI | 3.2 GB | 5.5 GB | $0.08/h GTX 1660 SUPER |
| wireguard qwen25 onnx int4 (patlegu)patlegu/wireguard-qwen25-onnx-int4 | ONNX Runtime GenAI | 3.2 GB | 5.5 GB | $0.08/h GTX 1660 SUPER |
| crowdsec qwen25 onnx int4 (patlegu)patlegu/crowdsec-qwen25-onnx-int4 | ONNX Runtime GenAI | 3.2 GB | 5.5 GB | $0.08/h GTX 1660 SUPER |
| oga (SamTheDev)SamTheDev/qwen2.5-3B-oga | ONNX Runtime GenAI | 2.4 GB | 4.5 GB | $0.08/h GTX 1660 SUPER |
| vLLM |
| 5.6 GB |
| 8.9 GB |
| $0.10/h RTX 3060 |
| Qwen2.5 Coder 7BQwen/Qwen2.5-Coder-7B | vLLM | 15 GB | 19.7 GB | $0.18/h 2x RTX 3060 |
| Qwen2.5 Math 7B InstructQwen/Qwen2.5-Math-7B-Instruct | vLLM | 15 GB | 19.4 GB | $0.18/h 2x RTX 3060 |
| Instruct 1MQwen/Qwen2.5-7B-Instruct-1M | vLLM | 15 GB | 19.7 GB | $0.18/h 2x RTX 3060 |
| Qwen2.5 Math 7BQwen/Qwen2.5-Math-7B | vLLM | 15 GB | 19.4 GB | $0.18/h 2x RTX 3060 |
| Qwen2.5 Coder 7B Instruct AWQ (Orion-zhen)Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ | vLLM | 5.7 GB | 9.1 GB | $0.10/h RTX 3060 |
| Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-7B-Instruct-bnb-4bit | vLLM | 5.5 GB | 8.9 GB | $0.10/h RTX 3060 |
| Qwen2.5 Coder 7B Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit | vLLM | 5.5 GB | 8.9 GB | $0.10/h RTX 3060 |
| Instruct unsloth bnb 4bit (unsloth)unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit | vLLM | 7.2 GB | 10.7 GB | $0.10/h RTX 3060 |
| Instruct FP8 dynamic (RedHatAI)RedHatAI/Qwen2.5-7B-Instruct-FP8-dynamic | vLLM | 8.7 GB | 12.4 GB | $0.14/h RTX A4000 |
| Instruct heretic (saidutta69)saidutta69/Qwen2.5-7B-Instruct-heretic | vLLM | 15 GB | 19.7 GB | $0.18/h 2x RTX 3060 |
| Qwen2.5 Coder 7B bnb 4bit (unsloth)unsloth/Qwen2.5-Coder-7B-bnb-4bit | vLLM | 5.5 GB | 8.9 GB | $0.10/h RTX 3060 |
| Instruct ONNX WebGPU (danyalmalik)danyalmalik/Qwen2.5-7B-Instruct-ONNX-WebGPU | ONNX Runtime GenAI | 5.2 GB | 8 GB | $0.09/h RTX 3060 |
| Qwen2.5 Coder 7B Instruct ONNX WebGPU (danyalmalik)danyalmalik/Qwen2.5-Coder-7B-Instruct-ONNX-WebGPU | ONNX Runtime GenAI | 5.2 GB | 8 GB | $0.09/h RTX 3060 |
| vLLM |
| 9.9 GB |
| 15 GB |
| $0.14/h RTX A4000 |
| Instruct unsloth bnb 4bit (unsloth)unsloth/Qwen2.5-14B-Instruct-unsloth-bnb-4bit | vLLM | 11 GB | 16.6 GB | $0.18/h 2x RTX 3060 |
| instruct int4 zp onnx (justinchuby)justinchuby/qwen2.5-14b-instruct-int4-zp-onnx | ONNX Runtime GenAI | 8.3 GB | 12.7 GB | $0.12/h Nvidia V100 |
| vLLM |
| 66 GB |
| 77.4 GB |
| $0.89/h 2x Nvidia A40 |
| QwQ 32B PreviewQwen/QwQ-32B-Preview | vLLM | 66 GB | 77.4 GB | $0.89/h 2x Nvidia A40 |
| QwQ 32B AWQQwen/QwQ-32B-AWQ | vLLM | 19 GB | 26.1 GB | $0.34/h 2x RTX 5060 Ti |
| Qwen2.5 Coder 32BQwen/Qwen2.5-Coder-32B | vLLM | 66 GB | 77.4 GB | $0.89/h 2x Nvidia A40 |
| Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-32B-Instruct-bnb-4bit | vLLM | 19 GB | 26 GB | $0.34/h 2x RTX 5060 Ti |
| QwQ 32B MLX 8bit (lmstudio-community)lmstudio-community/QwQ-32B-MLX-8bit | vLLM | 35 GB | 43.3 GB | $0.45/h Nvidia A40 |
| Qwen2.5 Coder 32B Instruct bnb 4bit (unsloth)unsloth/Qwen2.5-Coder-32B-Instruct-bnb-4bit | vLLM | 19 GB | 26 GB | $0.34/h 2x RTX 5060 Ti |