NVIDIA · 74B (9B active) · Mixture of Experts
Agentic vision MoE compressed from Nemotron 3.5 Super — 9B active, packed for 24 GB GPUs Check if your GPU or Mac can run Nemotron 3.5 Bolt 74B-A9B locally — 41.4 GB min, 68.9 GB recommended.
2026-10256K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 24.2 GB | low | — |
| Q3_K_M | 3 | 33.7 GB | moderate | — |
| Q4_K_M | 4 | 38.4 GB | good | — |
| Q5_K_M | 5 | 47.9 GB | good | — |
| Q6_K | 6 | 57.4 GB | excellent | — |
| Q8_0 | 8 | 76.3 GB | excellent | — |
| F16 | 16 | 152.1 GB | lossless | — |
Can I run Nemotron 3.5 Bolt 74B-A9B locally?
- Can I run Nemotron 3.5 Bolt 74B-A9B locally?
- Nemotron 3.5 Bolt 74B-A9B needs about 41.4 GB of memory at a minimum and 68.9 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Nemotron 3.5 Bolt 74B-A9B need?
- At Q4_K_M, Nemotron 3.5 Bolt 74B-A9B uses about 38.4 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.