Can I Run Qwen 2.5 Family on NVIDIA GeForce RTX 5090?
作者： Jakub Rusinowski · 最后更新： 2026年7月12日
Yes, comfortably — you'll have ~12.7 GB of headroom running Qwen 2.5 Coder 32B at Q4_K_M (19.3 GB, ~64 tok/s (est.)) with room for up to 32K context.
See what else this hardware can run →
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
NVIDIA GeForce RTX 5090 Specs
| VRAM | 32 GB |
| Memory Bandwidth | 1792 GB/s |
Qwen 2.5 Coder 32B on the NVIDIA GeForce RTX 5090: VRAM by quantization
| Quant | VRAM needed | Fits 32 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 65.9 GB | ✗ No | — | — |
| Q8_0 | 35.9 GB | ✗ No | — | — |
| Q6_K | 28.1 GB | ✓ Yes | 16K | — |
| Q5_K_M | 24.6 GB | ✓ Yes | 16K | — |
| Q4_K_M | 21.2 GB | ✓ Yes | 32K | — |
| Q3_K_M | 15.5 GB | ✓ Yes | 64K | — |
| Q2_K | 12.4 GB | ✓ Yes | 64K | — |
Assumes a 4K-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 · 128K 54.5 GB ✗. Past 128K it no longer fits 32 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Qwen 2.5 Coder 32B on 32 GB of system RAM, CPU only: runs comfortably.
Qwen 2.5 Family Sizes That Fit the NVIDIA GeForce RTX 5090
| Qwen 2.5 Coder 32B | Q4_K_M · 19.3 GB · ~64 tok/s (est.) |
| Qwen 2.5 14B Instruct | Q4_K_M · 8.5 GB · ~120 tok/s (est.) |
| Qwen 2.5 7B Instruct | Q4_K_M · 4.6 GB · ~185 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 Qwen 2.5 Family locally?
Yes, comfortably — you'll have ~12.7 GB of headroom running Qwen 2.5 Coder 32B at Q4_K_M (19.3 GB, ~64 tok/s (est.)) with room for up to 32K context.
What's the best Qwen 2.5 Family size for the NVIDIA GeForce RTX 5090?
Qwen 2.5 Coder 32B at Q4_K_M quantization (19.3 GB), estimated ~64 tokens/sec, up to 32K context.
Every Qwen 2.5 Family size on the NVIDIA GeForce RTX 5090
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| Qwen 2.5 72B Instruct | 43.5 GB | Runs at Q2_K | — |
| Qwen 2.5 Coder 32B | 19.3 GB | Runs | ~64 tok/s |
| Qwen 2.5 14B Instruct | 8.5 GB | Runs | ~120 tok/s |
| Qwen 2.5 7B Instruct | 4.6 GB | Runs | ~185 tok/s |
Qwen 2.5 Family on Other GPUs
- Qwen 2.5 Family on Apple M4
- Qwen 2.5 Family on Apple M2 Pro
- Qwen 2.5 Family on Apple M1 Pro
- Qwen 2.5 Family on Apple M5
- Qwen 2.5 Family on Apple M3 Pro
Popular Models on the NVIDIA GeForce RTX 5090
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | Qwen 2.5 Family Model Page | NVIDIA GeForce RTX 5090 GPU Page | Check Your Hardware