What GPU do you need to run Nemotron 3.5 Bolt 74B A9B?
74.89B params 256K max context VisionTool useReasoning
The smallest GPU memory that runs Nemotron 3.5 Bolt 74B A9B well is 84 GB (Q8_0, e.g. RTX PRO 5500 Blackwell). 14 of 132 GPUs run it well. It's a mixture-of-experts model, so all weights must fit in memory but speed depends only on the active experts.
VRAM needed per quantization
| Quantization | Weights | 16K context | 32K context | Full 256K |
|---|---|---|---|---|
| Q8_0 | 73.4 GB | 73.6 GB | 73.7 GB | 75.5 GB |
Weights plus fp16 KV cache. Leave ~1 GB headroom for the inference engine.
Cheapest GPUs that can run Nemotron 3.5 Bolt 74B A9B
Lowest launch MSRP among GPUs that run its smallest quantization (Q8_0) well, with at least 16K context.
As an Amazon Associate, I earn from qualifying purchases.
GPUs that can run Nemotron 3.5 Bolt 74B A9B
Best quantization that fits on each GPU, with the context and speed it gets. For chips with several memory sizes, the smallest that works is shown.
NVIDIA
- RTX PRO 5500 Blackwell 84 GB Q8_0 256K context · ~142 tok/s
- RTX PRO 6000 Blackwell 96 GB Q8_0 256K context · ~182 tok/s
- DGX Spark (GB 10) 128 GB Q8_0 256K context · ~28 tok/s
- RTX Spark 128 GB Q8_0 256K context · ~31 tok/s
AMD
- Ryzen AI Max (Strix Halo) 96 GB Q8_0 256K context · ~26 tok/s
- Ryzen AI Max 400 (Gorgon Halo) 128 GB Q8_0 256K context · ~28 tok/s
Apple
- M2 Max 96 GB Q8_0 256K context · ~41 tok/s
- M3 Max 96 GB Q8_0 256K context · ~31 tok/s
- M3 Ultra 96 GB Q8_0 256K context · ~83 tok/s
- M5 Ultra 96 GB Q8_0 256K context · ~122 tok/s
- M1 Ultra 128 GB Q8_0 256K context · ~81 tok/s
- M2 Ultra 128 GB Q8_0 256K context · ~81 tok/s
- M4 Max 128 GB Q8_0 256K context · ~56 tok/s
- M5 Max 128 GB Q8_0 256K context · ~62 tok/s