Written by Jakub Rusinowski · Last updated March 20, 2026
Technically yes, but not recommended
It loads, but it is not worth running — Cogito v1 70B at Q8_0 fits in 128 GB system RAM's 102.4 GB, yet the memory bandwidth limits it to ~0.9 tok/s (estimated), well below usable interactive speed.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~0.9 tok/s
| Usable memory for models | 102.4 GB |
| Memory bandwidth | 90 GB/s |
| Quant | Memory needed | Fits 102.4 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 143.5 GB | ✗ No | — | — | 140 GB |
| Q8_0 | 77.9 GB | ✓ Yes | 64K | ~0.9 tok/s | 74.4 GB |
| Q6_K | 60.9 GB | ✓ Yes | 128K | ~1.1 tok/s | 57.4 GB |
| Q5_K_M | 53.1 GB | ✓ Yes | 128K | ~1.3 tok/s | 49.6 GB |
| Q4_K_M | 45.7 GB | ✓ Yes | 128K | ~1.5 tok/s | 42.3 GB |
| Q3_K_M | 33.3 GB | ✓ Yes | 128K | ~2.1 tok/s | 29.8 GB |
| Q2_K | 26.5 GB | ✓ Yes | 128K | ~2.7 tok/s | 23 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Cogito v1 70B | 45.7 GB | ✓ Fits | ~1.5 tok/s |
| Cogito v1 32B | 22.3 GB | ✓ Fits | ~3.3 tok/s |
| Cogito v1 14B | 10.9 GB | ✓ Fits | ~7.1 tok/s |
| Cogito v1 8B | 6.7 GB | ✓ Fits | ~12.2 tok/s |
| Cogito v1 3B | 3.6 GB | ✓ Fits | ~27.6 tok/s |
llama.cpp (CPU build) or Ollama — both run without a GPU
It loads, but it is not worth running — Cogito v1 70B at Q8_0 fits in 128 GB system RAM's 102.4 GB, yet the memory bandwidth limits it to ~0.9 tok/s (estimated), well below usable interactive speed.
Q8_0 — it needs about 77.9 GB of the 102.4 GB available, downloads as roughly 74.4 GB, and runs at an estimated 0.9 tokens/sec with up to 64K of context.
Memory bandwidth. The model fits, but at 89.6 GB/s it can only be read fast enough for roughly 0.9 tokens/sec.
llama.cpp (CPU build) or Ollama — both run without a GPU
← Can I Run It? | Cogito v1 model page | Check your hardware