Can I Run EXAONE 3.5 on NVIDIA GeForce RTX 5090?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 29 września 2026
Yes, comfortably — EXAONE 3.5 32B at Q4_K_M needs 22.3 GB at 8K context (19.3 GB weights + 3 GB KV cache/overhead), leaving ~9.7 GB of the NVIDIA GeForce RTX 5090's 32 GB, at ~64 tok/s (est.), with room for up to 32K context.
See what else this hardware can run →
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
NVIDIA GeForce RTX 5090 Specs
| VRAM | 32 GB |
| Memory Bandwidth | 1792 GB/s |
EXAONE 3.5 32B on the NVIDIA GeForce RTX 5090: VRAM by quantization
| Quant | VRAM needed | Fits 32 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 66.9 GB | ✗ No | — | — |
| Q8_0 | 36.9 GB | ✗ No | — | Build for this |
| Q6_K | 29.2 GB | ✓ Yes | 16K | — |
| Q5_K_M | 25.6 GB | ✓ Yes | 16K | Build for this |
| Q4_K_M | 22.3 GB | ✓ Yes | 32K | Build for this |
| Q3_K_M | 16.6 GB | ✓ Yes | 32K | — |
| Q2_K | 13.5 GB | ✓ Yes | 32K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 32 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA GeForce RTX 5090: 8K 22.3 GB · 32K 28.7 GB. Every window this model publishes still fits 32 GB.
No compatible GPU? EXAONE 3.5 32B on 32 GB of system RAM, CPU only: runs comfortably.
EXAONE 3.5 Sizes That Fit the NVIDIA GeForce RTX 5090 (at 8K context)
| EXAONE 3.5 32B | Q4_K_M · 22.3 GB at 8K context · ~64 tok/s (est.) |
| EXAONE 3.5 7.8B | Q4_K_M · 6.6 GB at 8K context · ~176 tok/s (est.) |
| EXAONE 3.5 2.4B | Q4_K_M · 2.9 GB at 8K context · ~294 tok/s (est.) |
At 2 hrs/day, buying (~$1,999) beats renting at $0.34/hr after about 8.2 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the NVIDIA GeForce RTX 5090 enough to run EXAONE 3.5 locally?
Yes, comfortably — EXAONE 3.5 32B at Q4_K_M needs 22.3 GB at 8K context (19.3 GB weights + 3 GB KV cache/overhead), leaving ~9.7 GB of the NVIDIA GeForce RTX 5090's 32 GB, at ~64 tok/s (est.), with room for up to 32K context.
What's the best EXAONE 3.5 size for the NVIDIA GeForce RTX 5090?
EXAONE 3.5 32B at Q4_K_M quantization needs 22.3 GB at 8K context (19.3 GB weights + 3 GB KV cache/overhead), estimated ~64 tokens/sec, up to 32K context.
Every EXAONE 3.5 size on the NVIDIA GeForce RTX 5090
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| EXAONE 3.5 32B | 22.3 GB | Runs | ~64 tok/s |
| EXAONE 3.5 7.8B | 6.6 GB | Runs | ~176 tok/s |
| EXAONE 3.5 2.4B | 2.9 GB | Runs | ~294 tok/s |
EXAONE 3.5 on Other GPUs
- EXAONE 3.5 on Apple M4
- EXAONE 3.5 on Apple M2 Pro
- EXAONE 3.5 on Apple M1 Pro
- EXAONE 3.5 on Apple M5
- EXAONE 3.5 on Apple M3 Pro
Popular Models on the NVIDIA GeForce RTX 5090
- DeepSeek R1 on NVIDIA GeForce RTX 5090
- Qwen 3 on NVIDIA GeForce RTX 5090
- Qwen 2.5 Family on NVIDIA GeForce RTX 5090
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | EXAONE 3.5 Model Page | NVIDIA GeForce RTX 5090 GPU Page | VRAM calculator | Check Your Hardware