Qwen2.5 Omni 3B MNN — Hardware Requirements & GPU Compatibility
Chat
Qwen2.5 Omni 3B MNN is a 3B-parameter open language model from taobao-mnn in the Qwen 2.5 family. At BF16 it needs about 6.60 GB of VRAM — see which GPUs and Macs can run it below.
365 downloads
3 likesSpecifications
- Publisher
- taobao-mnn
- Family
- Qwen 2.5
- Parameters
- 3B
- Release Date
- 2025-09-01
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Qwen2.5 Omni 3B MNN Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 6.6 GB | — | 6.00 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Qwen2.5 Omni 3B MNN?
BF16 · 6.6 GBQwen2.5 Omni 3B MNN (BF16) requires 6.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 9+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Qwen2.5 Omni 3B MNN?
BF16 · 6.6 GB33 devices with unified memory can run Qwen2.5 Omni 3B MNN, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Qwen2.5 Omni 3B MNN need?
Qwen2.5 Omni 3B MNN requires 6.6 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 3B × 16 bits ÷ 8 = 6 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF166.6 GB- Can I run Qwen2.5 Omni 3B MNN on a Mac?
Qwen2.5 Omni 3B MNN requires at least 6.6 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Qwen2.5 Omni 3B MNN locally?
Yes — Qwen2.5 Omni 3B MNN can run locally on consumer hardware. At BF16 quantization it needs 6.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen2.5 Omni 3B MNN?
At BF16, Qwen2.5 Omni 3B MNN can reach ~442 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~99 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 6.6 × 0.55 = ~442 tok/s
Estimated speed at BF16 (6.6 GB)
~442 tok/s~99 tok/s~330 tok/s~273 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen2.5 Omni 3B MNN?
At BF16, the download is about 6.00 GB.
- Which GPUs can run Qwen2.5 Omni 3B MNN?
35 consumer GPUs can run Qwen2.5 Omni 3B MNN at BF16 (6.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 28 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Qwen2.5 Omni 3B MNN?
33 devices with unified memory can run Qwen2.5 Omni 3B MNN at BF16 (6.6 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.