Model · Alibaba Qwen

Qwen3 4B

4B · Q4_K_M · 2.3 GB · open weights · curated for general, coding · repo created 2025-08-05

Weights, context cache and runtime overhead at four reference contexts. The total is the model's own; what differs per machine is the usable memory it has to fit into.

All memory figures are estimates: measured quantized file size + computed context memory + runtime overhead, with a 12% safety margin on your hardware. Real usage varies with runtime version and settings.

Every tracked GPU and Mac at 8K and 32K context with a full-precision (f16) cache — the same engine as the finder and the GPU pages.

Runs comfortably (EXCELLENT or GOOD) on 14 of 14 tracked devices at 8K context.

GGUF is the quantized single-file format local runtimes load (Ollama, LM Studio, llama.cpp); our memory figures are measured from the linked GGUF file. The original repo holds full-precision safetensors — a much larger download meant for GPUs with far more memory.

More from Alibaba Qwen

• Qwen3.8 27BHeat 81
• Qwen3.8 Flash-NextHeat 73
• Qwen3 8BHeat 63
• Qwen3 0.6BHeat 57
• Qwen3-Coder 30B-A3BHeat 52
• Qwen3 32BHeat 52

Every tracked model →