Nemotron 3.5 Bolt 74B-A9B

Running Nemotron 3.5 Bolt 74B-A9B locally

At IQ2_XXS and 4K of context, Nemotron 3.5 Bolt 74B-A9B needs about 23.1 GB — 20.9 GB of weights, 0.03 GB of KV cache and a 2.1 GB activation buffer. The smallest cards in this index that clear that comfortably are 32 GB ones — 4 of them, from the RTX 5090 up — and 26 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 0.22 GB, taking the total to 23.3 GB. That is gentler than the parameter count suggests: only 8 of 88 layers keep a KV cache that grows with context, so the cache scales at a fraction of the usual rate. The model's native window is 256K; holding all of it at IQ2_XXS would need about 25 GB.

Which build to download

This index only tracks Nemotron 3.5 Bolt 74B-A9B in GGUF, across 1 level (IQ2_XXS). No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.

Common questions

How much VRAM does Nemotron 3.5 Bolt 74B-A9B need?

About 23.1 GB at IQ2_XXS with 4K of context and batch 1, rising to roughly 23.3 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.

Will Nemotron 3.5 Bolt 74B-A9B run on a 32GB GPU?

Yes — at IQ2_XXS and 4K context it needs about 23.1 GB, which leaves 8.9 GB spare on a RTX 5090, or on any of the other 32 GB cards here (4 in all). That is the smallest size in this index that clears it comfortably; 26 of 78 do.

Which quantization of Nemotron 3.5 Bolt 74B-A9B should I use?

IQ2_XXS is the only level in the index for this model, so there is nothing to choose between here. Note this is a mixture-of-experts model — all parameters must be resident even though only a fraction are active per token, so the memory cost follows the total, not the active count.