Can I Run EXAONE 3.5 on AMD Radeon RX 7900 XTX?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 12 lipca 2026
Yes, but it's tight — 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 ~1.7 GB of the AMD Radeon RX 7900 XTX's 24 GB, at ~28 tok/s (est.), with room for up to 8K context.
See what else this hardware can run →
lub porównaj w Vast.ai od $0.35/godz. (typical low · varies)
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
AMD Radeon RX 7900 XTX Specs
| VRAM | 24 GB |
| Memory Bandwidth | 960 GB/s |
EXAONE 3.5 32B on the AMD Radeon RX 7900 XTX: VRAM by quantization
| Quant | VRAM needed | Fits 24 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 66.9 GB | ✗ No | — | — |
| Q8_0 | 36.9 GB | ✗ No | — | Build for this |
| Q6_K | 29.2 GB | ✗ No | — | — |
| Q5_K_M | 25.6 GB | ✗ No | — | Build for this |
| Q4_K_M | 22.3 GB | ✓ Yes | 8K | 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 24 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 AMD Radeon RX 7900 XTX: 8K 22.3 GB · 32K 28.7 GB ✗. Past 32K it no longer fits 24 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? EXAONE 3.5 32B on 32 GB of system RAM, CPU only: runs comfortably.
EXAONE 3.5 Sizes That Fit the AMD Radeon RX 7900 XTX (at 8K context)
| EXAONE 3.5 32B | Q4_K_M · 22.3 GB at 8K context · ~28 tok/s (est.) |
| EXAONE 3.5 7.8B | Q4_K_M · 6.6 GB at 8K context · ~84 tok/s (est.) |
| EXAONE 3.5 2.4B | Q4_K_M · 2.9 GB at 8K context · ~158 tok/s (est.) |
At 2 hrs/day, buying (~$999) beats renting at $0.34/hr after about 4.1 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
EXAONE 3.5 on the AMD Radeon RX 7900 XTX — does it fit?
Yes, but it's tight — 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 ~1.7 GB of the AMD Radeon RX 7900 XTX's 24 GB, at ~28 tok/s (est.), with room for up to 8K context.
Which EXAONE 3.5 variant fits best on the AMD Radeon RX 7900 XTX?
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 ~28 tokens/sec, up to 8K context.
Every EXAONE 3.5 size on the AMD Radeon RX 7900 XTX
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| EXAONE 3.5 32B | 22.3 GB | Runs | ~28 tok/s |
| EXAONE 3.5 7.8B | 6.6 GB | Runs | ~84 tok/s |
| EXAONE 3.5 2.4B | 2.9 GB | Runs | ~158 tok/s |
EXAONE 3.5 on Other GPUs
Popular Models on the AMD Radeon RX 7900 XTX
- DeepSeek R1 on AMD Radeon RX 7900 XTX
- Qwen 3 on AMD Radeon RX 7900 XTX
- Qwen 2.5 Family on AMD Radeon RX 7900 XTX
VRAM Tier
Troubleshooting
- Ollama: "model requires more system memory than is available"
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | EXAONE 3.5 Model Page | AMD Radeon RX 7900 XTX GPU Page | VRAM calculator | Check Your Hardware