Can I Run Nemotron 3.5 on NVIDIA GeForce RTX 4090?
作者： Jakub Rusinowski · 最后更新： 2026年10月15日
Yes, but it's tight — Nemotron 3.5 Bolt 74B at IQ2_XXS QAD needs 22.9 GB at 8K context (22 GB weights + 0.9 GB KV cache/overhead), leaving ~1.1 GB of the NVIDIA GeForce RTX 4090's 24 GB, at ~194 tok/s (est.), with room for up to 128K context.
See what else this hardware can run →
或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)
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 4090 Specs
| VRAM | 24 GB |
| Memory Bandwidth | 1008 GB/s |
Nemotron 3.5 Bolt 74B on the NVIDIA GeForce RTX 4090: VRAM by quantization
| Quant | VRAM needed | Fits 24 GB? | Max context | Whole PC |
|---|---|---|---|---|
| BF16 | 150.6 GB | ✗ No | — | — |
| IQ2_XXS QAD | 22.9 GB | ✓ Yes | 128K | — |
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 IQ2_XXS QAD on the NVIDIA GeForce RTX 4090: 8K 22.9 GB · 32K 23.1 GB · 128K 23.9 GB. Every window this model publishes still fits 24 GB.
Nemotron 3.5 Sizes That Fit the NVIDIA GeForce RTX 4090 (at 8K context)
| Nemotron 3.5 Bolt 74B | IQ2_XXS QAD · 22.9 GB at 8K context · ~194 tok/s (est.) |
| Nemotron 3.5 Lightning 30B-A3B | Q4_K_M · 20.7 GB at 8K context · ~195 tok/s (est.) |
At 2 hrs/day, buying (~$1,599) beats renting at $0.34/hr after about 6.5 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
Nemotron 3.5 on the NVIDIA GeForce RTX 4090 — does it fit?
Yes, but it's tight — Nemotron 3.5 Bolt 74B at IQ2_XXS QAD needs 22.9 GB at 8K context (22 GB weights + 0.9 GB KV cache/overhead), leaving ~1.1 GB of the NVIDIA GeForce RTX 4090's 24 GB, at ~194 tok/s (est.), with room for up to 128K context.
Which Nemotron 3.5 variant fits best on the NVIDIA GeForce RTX 4090?
Nemotron 3.5 Bolt 74B at IQ2_XXS QAD quantization needs 22.9 GB at 8K context (22 GB weights + 0.9 GB KV cache/overhead), estimated ~194 tokens/sec, up to 128K context.
Popular Models on the NVIDIA GeForce RTX 4090
- DeepSeek R1 on NVIDIA GeForce RTX 4090
- Qwen 3 on NVIDIA GeForce RTX 4090
- Qwen 2.5 Family on NVIDIA GeForce RTX 4090
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? | Nemotron 3.5 Model Page | NVIDIA GeForce RTX 4090 GPU Page | VRAM calculator | Check Your Hardware