kev
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
Details
- External ID
- 1375069862
- Source
- GITHUB
- Company
- —
- Product
- kev
- Website domain
- github.com
- Launched
- Sept. 17, 2026
- Cohort
- —
- Upvotes
- 2052
- Upvotes percentile
- 0.9988470407378939
- Tags
- decision-model, jev, qwen3
- Fetched at
- Sept. 21, 2026, 5:02 p.m.
- Updated at
- Sept. 21, 2026, 5:02 p.m.
Enrichment
- Theme
- local AI inference and runtimes
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- small language model for macbook training and inference
- Manually corrected
- False
Could you build this?
No Fine-tuning and distilling a lightweight foundation model to run efficiently on Apple Silicon requires specialized ML research, data curation, and local quantization expertise.
What it would actually take: Requires an ML training pipeline using PyTorch/MLX or Transformers with custom LoRA/QLoRA recipes, a curated high-quality alignment dataset, and optimization for Apple Silicon via Apple MLX or llama.cpp/GGUF quantization. Deep understanding of tokenizer behavior, small model distillation dynamics, and memory-constrained inference is needed.
Competitors
Other products that read as similar to this one — 137 launches clear the similarity bar, closest 8 shown.
Attention rank: #3 of 138 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 264 days after the earliest competitor.
- jev-on-a-laptop · github · 2026-09-16 · 22 upvotes · similarity 0.51
- tinyjev · github · 2026-09-22 · 25 upvotes · similarity 0.48
- Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone · hn · 2026-08-03 · 312 upvotes · similarity 0.48
- QwenJev · github · 2026-09-21 · 33 upvotes · similarity 0.45
- bev-train · github · 2026-09-27 · 34 upvotes · similarity 0.44
- Shoehorn, a library to quantize an LLM to fit your Mac's VRAM · hn · 2026-08-14 · 6 upvotes · similarity 0.41
- laya-mps · github · 2026-09-21 · 22 upvotes · similarity 0.40
- Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s · hn · 2026-09-01 · 240 upvotes · similarity 0.40
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.