Qwen Alibaba Released 2024-09 chatinstructioncode

Qwen 2.5

Alibaba's flagship open weights. The strongest model in its size class for English, Chinese, code, math, and tool use.

Best for strongest 7B-32B on consumer hardware
Sizes 0.5B · 1.5B · 3B · 7B · 14B · 32B · 72B
Context 128K
License Apache 2.0 (most sizes)
Min VRAM (default size, Q4) 1 GB
Rec VRAM 8 GB

What is Qwen 2.5?

Qwen 2.5 is Alibaba's open-weights language model. Released in 2024-09, it ships in 7 sizes (0.5B, 1.5B, 3B, 7B, 14B, 32B, 72B) and is licensed Apache 2.0 (most sizes). The most popular use case is strongest 7B-32B on consumer hardware.

VRAM and hardware

The smallest 0.5B size needs at least 1 GB VRAM; the largest 72B needs around 5 GB.

Size Min VRAM (Q4_K_M) Recommended VRAM Tokens/sec on 3090
0.5B 1 GB 2 GB ~34 tok/s
1.5B 1 GB 2 GB ~34 tok/s
3B 1 GB 2 GB ~34 tok/s
7B 5 GB 8 GB ~25 tok/s
14B 9 GB 14 GB ~22 tok/s
32B 20 GB 30 GB ~17 tok/s
72B 44 GB 66 GB ~14 tok/s

How to run Qwen 2.5 locally

Option 1: Ollama (simplest)

ollama pull qwen-2-5
ollama run qwen-2-5

Option 2: Mullama (production)

mullama pull qwen-2-5
mullama run qwen-2-5

Option 3: llama.cpp (CLI)

# Download a GGUF from Hugging Face (search "qwen-2-5 gguf")
./llama-cli -m qwen-2-5.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("qwen-2-5.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

What you can build with Qwen 2.5

  • chat
  • code
  • RAG
  • agentic
  • multilingual

Hardware it fits on

  • Apple Silicon (8GB): 0.5B in MLX
  • Apple Silicon (16GB): 1.5B in MLX
  • Apple Silicon (32GB): 3B in MLX or GGUF
  • Apple Silicon (64GB+): 72B in MLX
  • RTX 3090 (24GB): 3B at Q4_K_M
  • RTX 4090 (24GB): same as 3090, ~30% faster
  • RTX 5090 (32GB): 3B at Q8_0
  • 2× RTX 6000 Ada (96GB total): 72B at Q4_K_M

Related models in the Qwen family

  • Qwen 2.5-Coder — 0.5B, 1.5B, 3B, 7B, 14B, 32B · best open-weight code model in 2024-2025
  • Qwen 3 — 0.6B, 1.7B, 4B, 8B, 14B, 30B, 32B, 235B · best all-round local LLM in 2025-2026
  • Qwen 3-Coder — 30B, 480B · long-context code agent workflows
  • Qwen 3 VL — 2B, 4B, 8B, 30B, 32B, 235B · frontier-class vision-language with thinking

Other models you might consider

  • Llama 3.1 (Meta) — 8B, general-purpose chat, agentic workflows, code
  • Llama 3.2 (Meta) — 1B, low-end hardware, mobile, edge deployment
  • Llama 3.2 Vision (Meta) — 11B, vision + chat on desktop GPUs
  • Llama 3.3 (Meta) — 70B, best-in-class 70B for desktops
  • Llama 4 (Meta) — Scout 17B (109B MoE), vision + long context (10M tokens)
  • DeepSeek R1 (DeepSeek) — 1.5B, reasoning, math, step-by-step problem solving