NVIDIA · Vision · 74B parameters · 9B active · OpenMDW-1.1
NVIDIA Nemotron 3.5 Bolt 74B-A9B
Needs 89 GB at FP8 / INT8. The smallest real configuration today is 4× RTX 3090 at Clore.ai, $0.25 per hour, about $183 a month at 730 hours.
Parameters74B9B active per token
Context256k tokensmaximum published
Checkpoint150 GBBF16, as published
LicenseOpenMDW-1.1check before commercial use
ReleasedOct 15, 2026documented date
Smallest configuration · FP8 / INT8
4× RTX 309096 GB VRAM · 93% used
- Per hour
- $0.25
- Per month
- $183
- Cheapest at
Clore.ai
What is documented about NVIDIA Nemotron 3.5 Bolt 74B-A9B
news checked 2026-10-27A VLM for local agentic tasks, compressed from Super VL 120B-A12B with Star Elastic. Card: '74B Total / 9B Active', up to 256K context, text, image and video input. Same 88-block hybrid layout (8 attention layers). 240 experts, 9 active per MoE layer. Card 'Release Date: Hugging Face 10/15/2026'. The '24GB' repo appeared 2026-10-07.
- https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
- https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16/raw/main/config.json
- https://huggingface.co/api/models/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16?blobs=true
Memory · 3 precisionsHow much VRAM it needs
Weights plus runtime overhead. The context dimension appears once the model's architecture is on file.
| Precision | Weights | Weights + headroom |
|---|---|---|
| BF16published checkpoint | 150 GB | 180 GB |
| FP8 / INT8estimated | 74 GB | 89 GB |
| INT4 / MXFP4estimated | 44 GB | 54 GB |
Cross-checked on Hugging Face Oct 28, 2026: 74.9B parameters in the safetensors headers, 149.8 GB of weight files. Method: weights as published at the native precision, verified on Hugging Face 2026-10-28; other precisions estimated at 1 (8-bit) and 0.6 (4-bit) bytes per parameter; × 1.2 runtime headroom; KV cache not added (architecture not readable).
Smallest configuration per GPU · 110 GPUs · cheapest eligible on-demand offer per GPU count, every provider on fileWhat it costs to run, GPU by GPU
The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| RTX 3090Best fit | 4× 24 GB96 GB total | 93% tight | $0.25 | $183 | Clore.aiTrust 46 · read Nov 2 · receipt · also Vast.ai $0.56, Edgevana $0.92 |
| Tesla V100 32GB | 4× 32 GB128 GB total | 69% | $0.27 | $196 |  Vast.aiTrust 78 · read Nov 2 · receipt · also Cyfuture AI $2.22, gcube $6.44 |
| RTX A6000 | 2× 48 GB96 GB total | 93% tight | $0.38 | $274 | Clore.aiTrust 46 · read Nov 2 · receipt · also Lium $0.84, Spheron $0.89 |
| Tesla P100 | 8× 16 GB128 GB total | 69% | $0.38 | $274 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 3060 | 8× 12 GB96 GB total | 93% tight | $0.43 | $312 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.64, AtmosCompute $1.01 |
| Quadro RTX 8000 | 2× 48 GB96 GB total | 93% tight | $0.48 | $354 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.56 |
| L40 | 2× 48 GB96 GB total | 93% tight | $0.54 | $391 | Vast.aiTrust 78 · read Nov 2 · receipt · also io.net $1.32, GPU.ai $1.56 |
| RTX PRO 6000 | 1× 96 GB96 GB total | 93% tight | $0.66 | $482 |  packet.ainot scored · read Nov 2 · receipt · also Runpod $0.69, HyperAI $0.80 |
| Titan RTX | 4× 24 GB96 GB total | 93% tight | $0.70 | $508 | Vast.aiTrust 78 · read Nov 2 · receipt |
| Tesla V100 16GB | 8× 16 GB128 GB total | 69% | $0.75 | $547 | Vast.aiTrust 78 · read Nov 2 · receipt · also CloudRift $2.32, Lambda $6.32 |
| L40S | 2× 48 GB96 GB total | 93% tight | $0.76 | $555 |  LiumTrust 40 · read Nov 2 · receipt · also Vast.ai $1.07, CloudRift $1.26 |
| RTX A5000 | 4× 24 GB96 GB total | 93% tight | $0.80 | $586 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $1.05 |
| RTX 5060 Ti | 8× 16 GB128 GB total | 69% | $0.82 | $596 | Clore.aiTrust 46 · read Nov 2 · receipt · also Vast.ai $0.86, Edgevana $0.98 |
| RTX PRO 4000 | 4× 24 GB96 GB total | 93% tight | $0.83 | $608 | Clore.aiTrust 46 · read Nov 2 · receipt · also Vast.ai $1.55, Edgevana $1.78 |
| RTX 4070 Super | 8× 12 GB96 GB total | 93% tight | $0.85 | $617 | Vast.aiTrust 78 · read Nov 2 · receipt · also AtmosCompute $1.36 |
| A40 | 2× 48 GB96 GB total | 93% tight | $0.94 | $683 | Vast.aiTrust 78 · read Nov 2 · receipt · also Exoscale $2.09 |
| A800 80GB PCIe | 2× 80 GB160 GB total | 55% | $0.96 | $702 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX PRO 5000 | 2× 48 GB96 GB total | 93% tight | $0.96 | $702 | Vast.aiTrust 78 · read Nov 2 · receipt · also Lium $1.70, AtmosCompute $2.04 |
| A10 | 4× 24 GB96 GB total | 93% tight | $0.96 | $703 | Vast.aiTrust 78 · read Nov 2 · receipt · also Volcano Engine $6.39 |
| RTX A4000 | 8× 16 GB128 GB total | 69% | $0.96 | $704 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 6000 Ada | 2× 48 GB96 GB total | 93% tight | $0.99 | $722 | Vast.aiTrust 78 · read Nov 2 · receipt · also GPU.ai $1.30, io.net $1.37 |
| Gaudi 2 | 1× 96 GB96 GB total | 93% tight | $1.06 | $777 |  Cyfuture AInot scored · read Nov 2 · receipt |
| RTX 4090 | 4× 24 GB96 GB total | 93% tight | $1.08 | $791 | Clore.aiTrust 46 · read Nov 2 · receipt · also Vast.ai $1.50, Lium $2.00 |
| L4 | 4× 24 GB96 GB total | 93% tight | $1.09 | $795 |  Infomaniaknot scored · read Nov 2 · receipt · also Vast.ai $1.98, OVHcloud $3.35 |
| The 24 cheapest of 60 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
NVIDIA Nemotron 3.5 Bolt 74B-A9B · related