estimate
Can I run NVIDIA Nemotron 3.5 Bolt 74B-A9B on an RTX 5090?
No: needs ~45.3 GB, this card has ~31.4 GB usable (estimate)
Can I run NVIDIA Nemotron 3.5 Bolt 74B-A9B on an RTX 5090? No: needs ~45.3 GB, this card has ~31.4 GB usable (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 | 31.4 GB estimate | no | — |
| 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 | 31.4 GB estimate | no | — |
| Q8 Q8 | 8,192 tokens | 79.2 GB estimate | 0.1 GB estimate | 0.8 GB estimate | 80.0 GB estimate | 31.4 GB estimate | no | — |
| FP16 FP16 | 8,192 tokens | 148.0 GB estimate | 0.1 GB estimate | 0.8 GB estimate | 148.9 GB estimate | 31.4 GB estimate | no | — |
| Q4, longer context | 32,768 tokens | 44.4 GB estimate | 0.3 GB estimate | 0.8 GB estimate | 45.5 GB estimate | 31.4 GB estimate | no | — |
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
$7,052€6,299
new (lowest in-stock EU)
price as of 16 Oct 2026
PriceSquirrelCheapest in-stock listing on 16 Oct 2026: €6,299, ASUS ROG Astral GeForce RTX 5090 32GB OC White at Proshop (FI). MSI Gaming Trio OC at Compumsa (BE) was €6,571 and out of stock. A 16 Oct 2026 fact-check notes BE/NL/DE about €7,900–€8,800. No used median was recorded. NVIDIA (Jeff Fisher, 16 Oct 2026) denies a production halt; supply is tight and some retailers have delisted the card.
Embed this
NVIDIA Nemotron 3.5 Bolt 74B-A9B on RTX 5090
[](https://localllmrig.com/can-i-run/nemotron-3-5-bolt-74b/rtx-5090?utm_source=badge)
Questions
- Can I run NVIDIA Nemotron 3.5 Bolt 74B-A9B on an RTX 5090?
- No: needs ~45.3 GB, this card has ~31.4 GB usable (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 RTX 5090 (estimate)?
- No tokens-per-second estimate. The Q4 fit is not full and not offload, so this page leaves speed blank.