Check my GPU

LLMs ·

Qwen2.5-Omni 3B

Parameters
5.5B
Architecture
Dense
Max context
32K tokens
License
qwen-research
Released
2025-04

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/Qwen2.5-Omni-3B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen2.5-Omni-3B-GGUF

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen2.5-Omni-3B (opens in a new tab)

No sign-in needed.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 2.2 GB 3.1 GB 4.0 GB GGUF (opens in a new tab)
Q3_K_M Low 2.7 GB 3.6 GB 4.5 GB GGUF (opens in a new tab)
Q4_K_M Good 3.4 GB 4.3 GB 5.2 GB GGUF (opens in a new tab)
Q5_K_M High 3.9 GB 4.8 GB 5.7 GB GGUF (opens in a new tab)
Q6_K High 4.5 GB 5.4 GB 6.4 GB GGUF (opens in a new tab)
Q8_0 Very high 5.9 GB 6.8 GB 7.7 GB GGUF (opens in a new tab)
F16 Full 11.1 GB 12.0 GB 12.9 GB GGUF (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Qwen2.5-Omni 3B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q3_K_M.

Grade · points Hardware Quant Memory Speed Fit
68 ptsGood (B) · 68 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti F16 12.8 GB / 16.0 GB 46.6 tok/s Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 F16 12.8 GB / 16.0 GB 49.9 tok/s Runs well
68 ptsGood (B) · 68 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Q6_K 5.8 GB / 8.0 GB 41.8 tok/s Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.2/15 NVIDIA GeForce RTX 3060 12GB Q8_0 7.4 GB / 12.0 GB 40.6 tok/s Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.2/15 NVIDIA GeForce RTX 4070 SUPER Q8_0 7.4 GB / 12.0 GB 56.9 tok/s Runs well
67 ptsGood (B) · 67 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 14.2/15 Intel Arc B580 Q8_0 7.4 GB / 12.0 GB 39.3 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15 AMD Radeon RX 7900 XTX F16 13.2 GB / 24.0 GB 43.0 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15 NVIDIA GeForce RTX 3090 F16 13.2 GB / 24.0 GB 48.7 tok/s Runs well
66 ptsGood (B) · 66 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15 NVIDIA GeForce RTX 4090 F16 13.2 GB / 24.0 GB 52.4 tok/s Runs well
64 ptsGood (B) · 64 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15 AMD Radeon RX 9070 XT Q8_0 7.6 GB / 16.0 GB 62.2 tok/s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.