Autor: Jakub Rusinowski · Ostatnia aktualizacja: 20 marca 2026
Model library → Cogito v1 → Cogito v1 32B
Flagship consumer Cogito variant. Scores 52.7% on AIME 2025 — higher than DeepSeek-R1 32B. Runs on a single RTX 3090 or 4090 (24 GB) at ~18 tokens/second. The best open reasoning model available on a single consumer GPU.
Cogito v1 32B needs about 20 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 | 32 Billion |
| Context window | 64,000 |
| Architecture | Hybrid Reasoning Transformer |
| Provider | Deep Cogito |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 48 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 | 10.5 GB | 13.5 GB | ~57 tok/s (est.) | Fits comfortably |
| Q3_K_M | 13.6 GB | 16.6 GB | ~46 tok/s (est.) | Fits comfortably |
| Q4_K_M | 19.3 GB | 22.3 GB | ~34 tok/s (est.) | Tight fit |
| Q5_K_M | 22.7 GB | 25.6 GB | ~4 tok/s (est.) | Offloads to system RAM (slow) |
| Q6_K | 26.2 GB | 29.2 GB | ~4 tok/s (est.) | Offloads to system RAM (slow) |
| Q8_0 | 34.0 GB | 36.9 GB | ~3 tok/s (est.) | Offloads to system RAM (slow) |
| F16 | 64.0 GB | 66.9 GB | — | Won't fit |
Want the memory numbers alone, at every quantization level and your own context length? Use the Cogito v1 32B 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 32B is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama, then run:
ollama run cogito:32bWeights on Hugging Face: deepcogito/Cogito-v1-32B-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 | 85.6 / 100 % | reported |
| MATH | 78.3 / 100 % | reported |
| AIME 2025 | 52.7 / 100 % | reported |
| HumanEval | 83.1 / 100 % | reported |
Best for: reasoning, math, coding, rtx 4090.
← All Cogito v1 models | VRAM calculator | Check your own hardware