Skip to content
localmodel.run

Text model · Qwen3

Qwen3 1.7B requirements

Qwen3 family · 1.7B params · released 2025-04-29 · 23M Ollama pulls. Minimum to run at Q4_K_M: Apple M1 (8GB).

LicenseApache-2.0· Commercial OK↓ 3.7M/mo♥ 485on HuggingFace
Q4_K_M
1.28 GB
Q8_0
2.17 GB
Total @ Q4 (4k)
~2.4 GB
Context
32 k

Quantization sizes

GGUF quantson disk
QuantizationSize on disk
Q2_K0.7 GB est
Q3_K_M0.8 GB est
Q4_K_M (default)1.28 GB
Q5_K_M1.2 GB est
Q6_K1.4 GB est
Q8_02.17 GB
FP163.4 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

Ollama
$ ollama run qwen3:1.7b
llama.cpp
$ llama-cli -hf bartowski/Qwen_Qwen3-1.7B-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/Qwen_Qwen3-1.7B-GGUF

Which devices can run Qwen3 1.7B?

FAQ

How much VRAM or RAM does Qwen3 1.7B need?

At Q4_K_M, Qwen3 1.7B needs about 2.4 GB (weights ~1.28 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~3.3 GB.

Can Qwen3 1.7B run on a laptop?

Yes, Qwen3 1.7B fits on a 16 GB machine at Q4_K_M and runs on Apple Silicon or a 12 GB+ GPU comfortably.

Can I use Qwen3 1.7B commercially?

Yes. Qwen3 1.7B is licensed Apache-2.0, which permits commercial use.

Dual-mode (thinking/non-thinking) 1.7B dense model. 32K native context (YaRN to 128K). Strong instruction-following and tool-use for its class.

Sources

Memory figures are estimates. See methodology.