compactApache 2.04B paramsOpen weights

Qwen3 4B

4B parameter open-weight model. Compact Qwen3 variant. Q4 fits in 4 GB VRAM. Best compact pick for chat and coding on constrained hardware.

Alibaba Cloud · Qwen3

Model overview

Qwen3 4B is a compact model from Alibaba's Qwen3 family, small enough to fit comfortably on entry-level consumer GPUs while still handling everyday chat, coding help, and summarization. Its 32K token context window is generous for a model this size, and it's released under the permissive Apache 2.0 license. It's a practical starting point if you're setting up local AI on a laptop GPU or an older desktop card, and it pairs well with Ollama or LM Studio for a quick first run. Compared to larger Qwen3 checkpoints, it trades some capability for a much smaller VRAM footprint — treat it as the compact pick for constrained hardware rather than the strongest model in the family.

Check your GPU fitWhat is VRAM?What is quantization?Local LLM quickstart

Editorial review

Reviewed byOpenSourcesAI EditorialLast updatedJune 2026SourcesHuggingFace model card (Qwen/Qwen3-4B), official docs, OpenSourcesAI editorial review.

VRAM figures are empirical estimates. Actual usage varies by runtime, context length, and system configuration. Verify on your specific hardware before production use.

Will Qwen3 4B run on your machine?

Qwen3 4B is 4B parameters and needs 4.1 GB of VRAM at Q4_K_M — 2.6 GB of weights plus 1.5 GB of runtime overhead for the inference server itself.

VRAM by quantization

QuantizationWeightsNeeds (with overhead)Quality
Q4_K_M2.6 GB4.1 GBgood
Q8_04.5 GB6 GBhigh
FP168 GB9.5 GBreference

Fit on common hardware at Q4_K_M

HardwareMemory the model can useSystem RAMVerdict
CPU OnlyNone (CPU only)16 GBCPU offload
RTX 4060 Laptop8 GB16 GBComfortable
RTX 3060 (12GB)12 GB32 GBComfortable
RTX 4060 Ti (16GB)16 GB32 GBComfortable

Comfortable means VRAM clears the requirement by 2 GB or more. Tight means it covers the requirement with no margin. CPU offload means the model does not fit in VRAM but system RAM is at least 1.6× the weights, so it will run at reduced speed — expect roughly 1–5 tokens per second. Figures are weights plus a fixed runtime overhead and exclude KV-cache growth, which scales with context length.

Check Qwen3 4B against your exact hardwareHow these verdicts are calculated

Need more hardware for Qwen3 4B? Open the PC Builder for the 7B / 8B tier →

Related models

Gemma 3 4B4B parameter model — shared focus: chat, summarisation, rag.VibeThinker-3B3B parameter model — shared focus: reasoning, math, coding.DeepSeek-R1 8B (0528 Qwen3)8B parameter model — shared focus: reasoning, coding, chat.Qwen2.5 14BBuilders hosting local AI on a single RTX 4080 (16 GB) or RTX 4090 (24 GB) who want near-frontier multilingual reasoning, mathematical accuracy, and agentic coding performance without multi-GPU infrastructure. The sweet spot between consumer accessibility and frontier-class open-weight capability for 2026 local deployment.

Ready to run this model locally?

Find a compatible interface in our Local AI Tools directory →