estimate
Can I run NVIDIA Nemotron 3.5 Bolt 74B-A9B on a Dual RTX 4090?
Yes, fully in VRAM (estimate)
Can I run NVIDIA Nemotron 3.5 Bolt 74B-A9B on a Dual RTX 4090? Yes, fully in VRAM (estimate). About 45.3 GB at Q4_K_M (estimate).
Updated . The later of the hardware price date and the formula date.
| Quant | Context | Weights | KV | Overhead | Total | Usable | Fit | Est. tok/s |
|---|---|---|---|---|---|---|---|---|
| Q4 Q4_K_M | 8,192 tokens | 44.4 GB estimate | 0.1 GB estimate | 0.8 GB estimate | 45.3 GB estimate | 46.8 GB estimate | full | 19.4 tok/s estimate |
| Q5 Q5 (~0.71 bytes/param) | 8,192 tokens | 52.5 GB estimate | 0.1 GB estimate | 0.8 GB estimate | 53.4 GB estimate | 46.8 GB estimate | offload | 5.1 tok/s estimate |
| Q8 Q8 | 8,192 tokens | 79.2 GB estimate | 0.1 GB estimate | 0.8 GB estimate | 80.0 GB estimate | 46.8 GB estimate | offload | 1.2 tok/s estimate |
| FP16 FP16 | 8,192 tokens | 148.0 GB estimate | 0.1 GB estimate | 0.8 GB estimate | 148.9 GB estimate | 46.8 GB estimate | offload | 0.4 tok/s estimate |
| Q4, longer context | 32,768 tokens | 44.4 GB estimate | 0.3 GB estimate | 0.8 GB estimate | 45.5 GB estimate | 46.8 GB estimate | full | 19.3 tok/s estimate |
Formula estimate, not a benchmark. Method →
community measurement, single run
Published 16 Oct 2026. NVIDIA official 2-bit GGUF, stated file size 22.0 GB. llama.cpp 0.7.0-dev build 11669, commit 620d2225c, 4K context, chat-short, one run per config, runs dated 15 Oct 2026. Headline figures are 87.8, 107.3 and 154.7 tokens per second. The table prints 87.75 for the RTX 3090 and says the quant was not reported in that column. Not a localLLMrig measurement. Calculator estimates keep benchmarkSourceUrl null.
| Hardware | Tokens per second |
|---|---|
| RTX 3090 | 87.8 tok/s community measurement, single run |
| RTX 4090 | 107.3 tok/s community measurement, single run |
| RTX 5090 | 154.7 tok/s community measurement, single run |
llm-speed, published 2026-10-16
This measurement stays separate from the formula estimate above.
Cheapest catalog option that fits at Q4
Mac mini M4 Pro 64GB, catalog price, €1,890, dated 2026-10-16. No buy link.
This hardware
$8,206€7,330
price as of 16 Oct 2026
128 GB DDR4 (estimate): $2,754€2,460. From the 16 Oct 2026 fact-check.
rest of system (estimate): $560€500. The total is the GPU price plus the RAM line plus this estimate. It is not a checked system price.
price unverifiedGPU line is 2× the used median €2,185 (€4,370), labelled used, from pcprice.watch (https://www.pcprice.watch/gpu-buying-guide/rtx-4090-price-used-and-specs). 128 GB DDR4 (estimate) €2,460, from the 16 Oct 2026 fact-check. Rest of system (estimate) €500. Other parts from €500 in that fact-check. Not a shop listing. DDR5 was not separately priced, so this total uses the sourced 128 GB DDR4 line. The total is the GPU price plus the RAM line plus that rest estimate. It is not a checked system price.
Embed this
NVIDIA Nemotron 3.5 Bolt 74B-A9B on Dual RTX 4090
[](https://localllmrig.com/can-i-run/nemotron-3-5-bolt-74b/dual-rtx-4090?utm_source=badge)
Questions
- Can I run NVIDIA Nemotron 3.5 Bolt 74B-A9B on a Dual RTX 4090?
- Yes, fully in VRAM (estimate).
- How much memory does NVIDIA Nemotron 3.5 Bolt 74B-A9B need at Q4?
- About 45.3 GB at 8,192 tokens (estimate): 44.4 GB weights, 0.1 GB KV cache, 0.8 GB overhead.
- How fast is NVIDIA Nemotron 3.5 Bolt 74B-A9B on Dual RTX 4090 (estimate)?
- About 19.4 tok/s at Q4 (estimate, not a benchmark).