Qwen3 1.7B for drowse

A chat model for drowse.ai, which runs it on the device through WebGPU and reads and steers it as it generates. This repository holds the converted weights, the tokenizer, the WebAssembly model library with drowse's hooks compiled in, and the core geometry pack (neutral statistics and the default concept manifolds for each context). Its R lens, S lens and units packs are in stdlogits/drowse-web-qwen3-1.7b-instruments.

Source: Qwen/Qwen3-1.7B
Weights: q4f32_1: 4-bit weights, float32 compute
Context: 2048 and 4096 tokens
Runtime: drowse-web-runtime-v2, hook ABI block-sites-v5, profile standard-v4

These are browser artifacts, not a Transformers checkpoint. Install them through drowse.ai: its signed catalog pins each download to an immutable revision of this repository and verifies every file's SHA-256 digest.

Reproducibility and licenses

drowse-build.json records the exact source files, the MLC LLM base commit and every compiler overlay's hash; hosted-artifacts.json and hosted-pack-artifacts.json list every file with its digest. The model library is compiled by the recipe in browser-runtime/ of stdlogits/drowse.ai, which pins the upstream TVM, MLC LLM and WebLLM sources and the patches drowse applies to them. Licenses apply by component: see LICENSES.md.

drowse is written by a9lim with Claude; its browser edition, drowse.ai, is built from stdlogits/drowse.ai.

Downloads last month: -

Model tree for stdlogits/drowse-web-qwen3-1.7b

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Quantized

(452)

this model