Can I Run Qwen 3.5 on NVIDIA GeForce RTX 3090?
作者： Jakub Rusinowski · 最后更新： 2026年7月12日
Yes, but it's tight — Qwen 3.5 35B-A3B at Q4_K_M needs 21.1 GB of the NVIDIA GeForce RTX 3090's 24 GB, leaving only ~2.9 GB, ~144 tok/s (est.) with room for up to 8K 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 3090 Specs
| VRAM | 24 GB |
| Memory Bandwidth | 936 GB/s |
Qwen 3.5 35B-A3B on the NVIDIA GeForce RTX 3090: VRAM by quantization
| Quant | VRAM needed | Fits 24 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 71.7 GB | ✗ No | — | — |
| Q8_0 | 38.9 GB | ✗ No | — | Build for this |
| Q6_K | 30.4 GB | ✗ No | — | — |
| Q5_K_M | 26.5 GB | ✗ No | — | Build for this |
| Q4_K_M | 22.9 GB | ✓ Yes | 8K | Build for this |
| Q3_K_M | 16.7 GB | ✓ Yes | 32K | — |
| Q2_K | 13.2 GB | ✓ Yes | 32K | — |
Assumes a 4K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. 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 NVIDIA GeForce RTX 3090: 8K 23.8 GB · 32K 29.4 GB ✗ · 128K 52 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? Qwen 3.5 35B-A3B on 32 GB of system RAM, CPU only: runs, but it is tight.
Qwen 3.5 Sizes That Fit the NVIDIA GeForce RTX 3090
| Qwen 3.5 35B-A3B | Q4_K_M · 21.1 GB · ~144 tok/s (est.) |
| Qwen 3.5 27B | Q4_K_M · 16.3 GB · ~32 tok/s (est.) |
| Qwen 3.5 9B | Q4_K_M · 5.4 GB · ~79 tok/s (est.) |
| Qwen 3.5 4B | Q4_K_M · 2.4 GB · ~139 tok/s (est.) |
| Qwen 3.5 2B | Q4_K_M · 1.2 GB · ~202 tok/s (est.) |
| Qwen 3.5 0.8B | Q4_K_M · 0.5 GB · ~283 tok/s (est.) |
At 2 hrs/day, buying (~$1,499) beats renting at $0.34/hr after about 6.1 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
Qwen 3.5 on the NVIDIA GeForce RTX 3090 — does it fit?
Yes, but it's tight — Qwen 3.5 35B-A3B at Q4_K_M needs 21.1 GB of the NVIDIA GeForce RTX 3090's 24 GB, leaving only ~2.9 GB, ~144 tok/s (est.) with room for up to 8K context.
Which Qwen 3.5 variant fits best on the NVIDIA GeForce RTX 3090?
Qwen 3.5 35B-A3B at Q4_K_M quantization (21.1 GB), estimated ~144 tokens/sec, up to 8K context.
Every Qwen 3.5 size on the NVIDIA GeForce RTX 3090
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| Qwen 3.5 397B-A17B | 134 GB | Does not fit | — |
| Qwen 3.5 122B-A10B | 73.7 GB | Does not fit | — |
| Qwen 3.5 35B-A3B | 21.1 GB | Runs | ~144 tok/s |
| Qwen 3.5 27B | 16.3 GB | Runs | ~32 tok/s |
| Qwen 3.5 9B | 5.4 GB | Runs | ~79 tok/s |
| Qwen 3.5 4B | 2.4 GB | Runs | ~139 tok/s |
| Qwen 3.5 2B | 1.2 GB | Runs | ~202 tok/s |
| Qwen 3.5 0.8B | 0.5 GB | Runs | ~283 tok/s |
Qwen 3.5 on Other GPUs
- Qwen 3.5 on NVIDIA GeForce RTX 4090
- Qwen 3.5 on AMD Radeon RX 7900 XTX
- Qwen 3.5 on Apple M4 Pro
- Qwen 3.5 on Apple M3
- Qwen 3.5 on Apple M2
Popular Models on the NVIDIA GeForce RTX 3090
- DeepSeek R1 on NVIDIA GeForce RTX 3090
- Qwen 3 on NVIDIA GeForce RTX 3090
- Qwen 2.5 Family on NVIDIA GeForce RTX 3090
VRAM Tier
Troubleshooting
- CUDA out of memory — why it happens and how to fix it
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | Qwen 3.5 Model Page | NVIDIA GeForce RTX 3090 GPU Page | Check Your Hardware