Autor: Jakub Rusinowski · Ostatnia aktualizacja: 20 marca 2026
Model library → Cogito v1 → Cogito v1 14B
14B Cogito variant for 12–16 GB VRAM setups. On AIME 2025, Cogito v1-14B scores comparably to Qwen QwQ-32B — a remarkable result for a non-MoE 14B model. Ideal for developers wanting strong mathematical reasoning on a midrange GPU.
Cogito v1 14B needs about 9 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 | 14 Billion |
| Context window | 64,000 |
| Architecture | Hybrid Reasoning Transformer |
| Provider | Deep Cogito |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 24 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 | 4.6 GB | 7.0 GB | ~106 tok/s (est.) | Fits comfortably |
| Q3_K_M | 6.0 GB | 8.4 GB | ~89 tok/s (est.) | Fits comfortably |
| Q4_K_M | 8.5 GB | 10.9 GB | ~69 tok/s (est.) | Fits comfortably |
| Q5_K_M | 9.9 GB | 12.3 GB | ~61 tok/s (est.) | Fits comfortably |
| Q6_K | 11.5 GB | 13.9 GB | ~54 tok/s (est.) | Fits comfortably |
| Q8_0 | 14.9 GB | 17.3 GB | ~44 tok/s (est.) | Fits comfortably |
| F16 | 28.0 GB | 30.4 GB | ~4 tok/s (est.) | Offloads to system RAM (slow) |
Want the memory numbers alone, at every quantization level and your own context length? Use the Cogito v1 14B 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 14B is the Intel Arc B570 (10 GB).
Install Ollama, then run:
ollama run cogito:14bWeights on Hugging Face: deepcogito/Cogito-v1-14B-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 | 81.2 / 100 % | reported |
| MATH | 72.6 / 100 % | reported |
| AIME 2025 | 38.4 / 100 % | reported |
Best for: reasoning, math, coding, midrange gpu.
← All Cogito v1 models | VRAM calculator | Check your own hardware