Written by Jakub Rusinowski · Last updated July 21, 2026
Yes
Yes — Cosmos 3 Nano at Q8_0 needs about 19.2 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) (~4.8 GB spare), at ~69.2 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~69.2 tok/s
| Usable memory for models | 24 GB |
| Memory bandwidth | 1008 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 24 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 34.2 GB | ✗ No | — | — | 32 GB |
| Q8_0 | 19.2 GB | ✓ Yes | 16K | ~69.2 tok/s | 17 GB |
| Q6_K | 15.4 GB | ✓ Yes | 16K | ~84.2 tok/s | 13.1 GB |
| Q5_K_M | 13.6 GB | ✓ Yes | 16K | ~93.5 tok/s | 11.3 GB |
| Q4_K_M | 11.9 GB | ✓ Yes | 16K | ~104.3 tok/s | 9.7 GB |
| Q3_K_M | 9.1 GB | ✓ Yes | 16K | ~129.7 tok/s | 6.8 GB |
| Q2_K | 7.5 GB | ✓ Yes | 16K | ~149.7 tok/s | 5.3 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Cosmos 3 Super | 41.8 GB | ✗ Too large | — |
| Cosmos 3 Nano | 11.9 GB | ✓ Fits | ~104.3 tok/s |
| Cosmos 3 Edge | 4.1 GB | ✓ Fits | ~225.1 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes — Cosmos 3 Nano at Q8_0 needs about 19.2 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) (~4.8 GB spare), at ~69.2 tok/s (estimated), with room for about 16,384 tokens of context.
Q8_0 — it needs about 19.2 GB of the 24 GB available, downloads as roughly 17 GB, and runs at an estimated 69.2 tokens/sec with up to 16K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving