Model · language model
Jeff-Qwen3.5-0.8B
Jeff-Qwen3.5-0.8B is a language model from Independent project (MIT license), first covered on 28 September 2026. It is available as open weights you can download and run (licence: Apache 2.0 (weights), MIT (code)).
Last updated
At a glance
- Made by
- Independent project (MIT license)
- Type
- Language model
- Availability
- Open weights
- Licence
- Apache 2.0 (weights), MIT (code)
- Context window
- Not stated
- First seen
- 28 September 2026
- Official page
- huggingface.co/mstrasser/Jeff-Qwen3.5-0.8B ↗
Taken from the coverage, not from our own testing; "not stated" means none of the reports we read gave it. All tracked models →
1 story about Jeff-Qwen3.5-0.8B
-
Open-source decision models Jeff-Qwen3.5-0.8B and Jeff-Gemma4-E2B run in ~30ms on local hardware
Jeff is a set of small, fast decision models fine-tuned from Qwen3.5 and Gemma 4, designed for zero-shot classification tasks. The 0.8B-parameter model runs in about 22ms on an RTX PRO 6000 and 28ms on an Apple M4 Max,…
1 source primary source HN 59github.com
