Qwen 3 1.7B
Qwen3-1.7B is the mid-tier dense model in Qwen3, sharing the same hybrid thinking architecture and 40K context as the 0.6B but with ~3x the parameters for noticeably stronger reasoning, math, and code. It targets the consumer-laptop sweet spot where a single 4-bit GGUF fits under 1.5GB of RAM.
Our default recommendation when 0.6B is not smart enough but you cannot afford 3B+. Qwen3-1.7B clears the bar for a usable local agent: it follows multi-turn tool plans, handles non-English prompts cleanly, and the Apache license makes it trivial to ship.
Overview
Qwen3-1.7B is the mid-tier dense model in Qwen3, sharing the same hybrid thinking architecture and 40K context as the 0.6B but with ~3x the parameters for noticeably stronger reasoning, math, and code. It targets the consumer-laptop sweet spot where a single 4-bit GGUF fits under 1.5GB of RAM.
Strengths
- Best-in-class reasoning per parameter at the 1-2B tier
- Apache-2.0 with no acceptable-use lock-in
- Works as a usable agent backbone (function calling is in the chat template)
- Strong multilingual coverage including CJK and Indic
Weaknesses
- Thinking traces are verbose and increase TTFT meaningfully
- Below Qwen3-4B/8B on hard math and long-horizon coding
- No vision modality
- Slightly less RAM-efficient than Llama-3.2-1B due to vocab size
Quantization variants
Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.
| Quantization | File size | VRAM required |
|---|---|---|
| Q4_K_M | 0.9 GB | 2 GB |
Get the model
HuggingFace
Original weights
Source repository — direct quantization required.
Hardware that runs this
Cards with enough VRAM for at least one quantization of Qwen 3 1.7B.
Models worth comparing
Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.
Frequently asked
What's the minimum VRAM to run Qwen 3 1.7B?
Can I use Qwen 3 1.7B commercially?
What's the context length of Qwen 3 1.7B?
Source: huggingface.co/Qwen/Qwen3-1.7B
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.
Related — keep moving
Verify Qwen 3 1.7B runs on your specific hardware before committing money.