Bosun — local AI model by Hanno Labs
Written by Jakub Rusinowski · Last updated
Hanno Labs' small decision models: rank-16 LoRAs on Qwen3-0.6B and Qwen3-1.7B with 256 learned decision tokens, so one question can carry up to 255 candidates. Served by the Jev-compatible server at /v1/systemone.
Variants
The smallest Bosun variant needs about 1 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Bosun v3.1 0.6B → 0.6B | ~1.2 GB | Not published | jev-compatible-server :8000 | |
| Bosun v3.1 1.7B → 1.7B | ~2 GB | Not published | jev-compatible-server :8000 |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Bosun locally
Install Ollama, then pull the tag.
Served by jev-compatible-server (default port 8000). This model does not run in Ollama.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Bosun v3.1 0.6B, Bosun v3.1 1.7BRecommended GPU
The cheapest catalogued GPU that runs Bosun locally (min 1 GB VRAM) is the Intel Arc B570 (10 GB).
Bosun — frequently asked questions
How much VRAM does Bosun need?
Bosun needs about 1 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Bosun v3.1 0.6B (1 GB, Q4_K_M); Bosun v3.1 1.7B (2 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Bosun on an RTX 4090 (24 GB)?
Yes — Bosun runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Bosun?
Q4_K_M is the best balance of quality and VRAM for Bosun in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run Bosun locally?
Bosun is a decision model: it is called over an HTTP endpoint (/v1/systemone), not chatted with. Where a variant is available in Ollama 0.35 or newer, pull it with `ollama pull` and send requests to the local server; the others ship their own server. Each variant page shows the exact commands for that model.