Nimble — local AI model by Bespoke Labs
Written by Jakub Rusinowski · Last updated
Bespoke Labs' 9B decision model, a LoRA on Qwen3.5-9B trained with contrastive data pairs. The default decision model in Ollama's library.
Variants
The smallest Nimble variant needs about 7 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| Nimble 9B → 9B | ~6.6 GB | 8K (prompt limit) | ollama pull nimble |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run Nimble locally
Install Ollama, then pull the tag.
ollama pull nimblePick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: Nimble 9BRecommended GPU
The cheapest catalogued GPU that runs Nimble locally (min 7 GB VRAM) is the Intel Arc B570 (10 GB).
Nimble — frequently asked questions
How much VRAM does Nimble need?
Nimble needs about 7 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Nimble 9B (7 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Nimble on an RTX 4090 (24 GB)?
Yes — Nimble 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 Nimble?
Q4_K_M is the best balance of quality and VRAM for Nimble 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 Nimble locally?
Nimble 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.