Autor: Jakub Rusinowski · Ostatnia aktualizacja: 20 marca 2026
Model library → Cogito v1 → Cogito v1 3B
Entry-level Cogito variant for edge devices and 4–6 GB VRAM GPUs. Despite its small size, the dynamic reasoning toggle outperforms Llama 3.2 3B on math and logic tasks. Runs on laptop integrated graphics (NPU-accelerated). Great for offline assistants.
Cogito v1 3B needs about 3 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 3 Billion |
| Context window | 32,000 |
| Architecture | Hybrid Reasoning Transformer |
| Provider | Deep Cogito |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 8 GB |
| Record updated | 2026-03-20 |
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB), at 8K context. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 1.0 GB | 2.7 GB | ~240 tok/s (est.) | Fits comfortably |
| Q3_K_M | 1.3 GB | 3.0 GB | ~219 tok/s (est.) | Fits comfortably |
| Q4_K_M | 1.8 GB | 3.6 GB | ~190 tok/s (est.) | Fits comfortably |
| Q5_K_M | 2.1 GB | 3.9 GB | ~176 tok/s (est.) | Fits comfortably |
| Q6_K | 2.5 GB | 4.2 GB | ~163 tok/s (est.) | Fits comfortably |
| Q8_0 | 3.2 GB | 4.9 GB | ~141 tok/s (est.) | Fits comfortably |
| F16 | 6.0 GB | 7.7 GB | ~93 tok/s (est.) | Fits comfortably |
Want the memory numbers alone, at every quantization level and your own context length? Use the Cogito v1 3B VRAM calculator.
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs Cogito v1 3B is the Intel Arc B570 (10 GB).
Install Ollama, then run:
ollama run cogito:3bWeights on Hugging Face: deepcogito/Cogito-v1-3B-Instruct.
Quality scores as published by the model's authors or an independent evaluator — not throughput, and not measured by us.
| Benchmark | Score | Provenance |
|---|---|---|
| MMLU | 66.8 / 100 % | reported |
| MATH | 52.4 / 100 % | reported |
Best for: edge devices, offline assistant, mobile, low power.
← All Cogito v1 models | VRAM calculator | Check your own hardware