# qwen3-1.7b Public Fork 0 Star 8 [Use Model in LM Studio](/content/deeplink?owner=qwen&name=qwen3-1.7b) [Model](/content/models/qwen/qwen3-1.7b ""/index.html) [Revisions](/content/qwen/qwen3-1.7b/revisions ""/index.html) Description The 1.7B parameter version of the Qwen3 model family. Stats 69.8KDownloads [8stars](/content/qwen/qwen3-1.7b/stars/index.html) Capabilities Trained for tool use ReasoningSupports reasoning Minimum system memory 1GB Tags 2B qwen3 Last updated [Updated on May 24](/content/qwen/qwen3-1.7b/revisions ""/index.html) by \\ \\ lmmy](/content/lmmy ""/index.html) [Report](/content/qwen/qwen3-1.7b/report ""/index.html) README FormattedRaw ## Qwen3 1.7B by qwen [Link to 'Qwen3 1.7B by qwen'](/content/models/qwen/qwen3-1.7b\#qwen3-17b-by-qwen "Link to 'Qwen3 1.7B by qwen'"/index.html) Supports a context length of up to 32k tokens Supports `/no_think` to disable reasoning, just add it at the end of your prompt Supports both thinking and non-thinking modes withe enhanced reasoning in both for significantly enhanced mathematics, coding, and commonsense Excels at creative writing, role-playing, multi-turn dialogues, and instruction following Advanced agent capabilities and support for over 100 languages and dialects Custom Fields Special features defined by the model author Enable Thinking : boolean (default=true) Controls whether the model will think before replying Parameters Custom configuration options included with this model Min P Sampling 0 Top K Sampling 20 Sources The underlying model files this model uses Based on 🤗 [lmstudio-community/Qwen3-1.7B-GGUF](https://huggingface.co/lmstudio-community/Qwen3-1.7B-GGUF) → GGUF 🤗 [lmstudio-community/Qwen3-1.7B-MLX-4bit](https://huggingface.co/lmstudio-community/Qwen3-1.7B-MLX-4bit) → MLX 🤗 [lmstudio-community/Qwen3-1.7B-MLX-8bit](https://huggingface.co/lmstudio-community/Qwen3-1.7B-MLX-8bit) → MLX 🤗 [lmstudio-community/Qwen3-1.7B-MLX-bf16](https://huggingface.co/lmstudio-community/Qwen3-1.7B-MLX-bf16) → MLX