作者： Jakub Rusinowski · 最后更新： 2025年4月5日
Yes, comfortably — you'll have ~8 GB of headroom running Llama 4 Maverick 17B at Q4_K_M (24 GB, ~400 tok/s (est.)).
在亚马逊查看价格 — NVIDIA GeForce RTX 5090 32GB
| VRAM | 32 GB |
| Memory Bandwidth | 1792 GB/s |
| Quant | VRAM needed | Fits 32 GB? | Max context |
|---|---|---|---|
| F16 | 928.8 GB | ✗ No | — |
| Q8_0 | 553.8 GB | ✗ No | — |
| Q6_K | 456.8 GB | ✗ No | — |
| Q5_K_M | 412.3 GB | ✗ No | — |
| Q4_K_M | 370.3 GB | ✗ No | — |
| Q3_K_M | 299.3 GB | ✗ No | — |
| Q2_K | 260.3 GB | ✗ No | — |
VRAM needed assumes a 4K-token context with an f16 KV cache; “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.
| Llama 4 Maverick 17B | Q4_K_M · 24 GB · ~400 tok/s (est.) |
| Llama 4 Scout 17B | Q4_K_M · 10.5 GB · ~400 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.
Yes, comfortably — you'll have ~8 GB of headroom running Llama 4 Maverick 17B at Q4_K_M (24 GB, ~400 tok/s (est.)).
Llama 4 Maverick 17B at Q4_K_M quantization (24 GB), estimated ~400 tokens/sec.
← Can I Run It? | Llama 4 Model Page | NVIDIA GeForce RTX 5090 GPU Page | Check Your Hardware