Written by Jakub Rusinowski · Last updated February 10, 2026
Yes, but it is tight
Yes, but it is tight — EXAONE 3.5 32B at Q6_K needs about 29.2 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~2.8 GB before the runtime starts swapping. Expect ~44.3 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~44.3 tok/s
| Usable memory for models | 32 GB |
| Memory bandwidth | 1792 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 66.9 GB | ✗ No | — | — | 64 GB |
| Q8_0 | 36.9 GB | ✗ No | — | — | 34 GB |
| Q6_K | 29.2 GB | ✓ Yes | 16K | ~44.3 tok/s | 26.2 GB |
| Q5_K_M | 25.6 GB | ✓ Yes | 16K | ~50.2 tok/s | 22.7 GB |
| Q4_K_M | 22.3 GB | ✓ Yes | 32K | ~57.4 tok/s | 19.3 GB |
| Q3_K_M | 16.6 GB | ✓ Yes | 32K | ~75.8 tok/s | 13.6 GB |
| Q2_K | 13.5 GB | ✓ Yes | 32K | ~92 tok/s | 10.5 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| EXAONE 3.5 32B | 22.3 GB | ✓ Fits | ~57.4 tok/s |
| EXAONE 3.5 7.8B | 6.6 GB | ✓ Fits | ~162.6 tok/s |
| EXAONE 3.5 2.4B | 2.9 GB | ✓ Fits | ~281 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, but it is tight — EXAONE 3.5 32B at Q6_K needs about 29.2 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~2.8 GB before the runtime starts swapping. Expect ~44.3 tok/s (estimated), with room for about 16,384 tokens of context.
Q6_K — it needs about 29.2 GB of the 32 GB available, downloads as roughly 26.2 GB, and runs at an estimated 44.3 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
← Can I Run It? | EXAONE 3.5 model page | Check your hardware