Nemotron 3.5 Bolt 74B-A9B
Oct 2026
Nemotron 3.5 Bolt 74B-A9BCompare inon
Nemotron 3.5 Bolt 74B-A9B measured on 5 of 42 Agents & Tool Use benchmarks5
BenchmarkByScoreRank
Agents4
Documents1
No benchmark matches
—per task?
self-host onlyprice
—output speed?
256Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.6 Lunamedium+49%—$0.016
OpenQwen3.8 Flashthinking×3.6—$0.37Memory (4-bit): 45 GB → 108 GB+6BetterGPT-6 Lunamedium×2.6—$0.017Function calling only with none · Chat Completions+3
BetterMiMo v2.5thinkingOpen+19%—$0.019Memory (4-bit): 45 GB → 186 GB
BetterClaude Haiku 5.5low+48%—$0.024Remove sampling parameters+5ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5.6 Lunamedium+49%—$0.016GPT-6 Lunamedium×2.6—$0.017Function calling only with none · Chat Completions+3MiMo v2.5thinkingOpen+19%—$0.019Memory (4-bit): 45 GB → 186 GBClaude Haiku 5.5low+48%—$0.024Remove sampling parameters+5MiMo v2.6 FlashthinkingOpen×4.1—$0.062Memory (4-bit): 45 GB → 186 GB+4ModelScoreCostPer taskWhat changes
Qwen3.8 FlashthinkingOpen×3.6—$0.37Memory (4-bit): 45 GB → 108 GB+6Qwen3.8 27BxhighOpen×3.1—$1.01max_tokens range · QwenCloud+4IK2 Horizon MoVA 36B A4BthinkingOpen+69%—$1 / $4No image inputIK2 Horizon 7BthinkingOpen+35%—$0.30 / $1.20No image input
Ling 3.0 Flash VLthinkingOpensame—$0.06 / $0.18Memory (4-bit): 45 GB → 75 GBModelScoreCostPer taskWhat changes
Nemotron 3.5 Super VLOpensame—$0.19Memory (4-bit): 45 GB → 75 GBNemotron 3 Super 120B A12BOpen-76%—$1.64Memory (4-bit): 45 GB → 74 GB+1Nemotron 3 UltrathinkingOpen-81%—$0.58Memory (4-bit): 45 GB → 336 GB+1Nemotron 3 Nano 30B A3BthinkingOpen-94%—$0.017Context: 256K → 131K+1Nemotron 3.5 LightningthinkingOpen-95%—$0.079No image inputNVIDIA Nemotron 3 Nano 4BOpen-97%——No image inputNemotron 3 Nano Omni 30B A3B ReasoningOpenn/a—$0 / $0Nemotron Cascade 2 30B A3BOpenn/a——No image inputAll NVIDIA models →Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✓ 48 GB GPU · compressed✓ 80 GB GPU · 8-bit
Licenceopenmdw-1.1commercial use with conditions
Benchmarks
in Agents & Tool UseAA-LCR (long context) 1.169.7#126
AutomationBench-AA15.5#67
AA-Briefcase 1.1 · Elo911.9#65
FAQ
How much does Nemotron 3.5 Bolt 74B-A9B cost?›
There is no per-unit API price: self-host only.
Is Nemotron 3.5 Bolt 74B-A9B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Nemotron 3.5 Bolt 74B-A9B, and what is it best at?›
#101 of 334 in Chat & Knowledge, #75 of 132 in Coding, #67 of 133 in Agents & Tool Use, #102 of 133 in Vision & Documents.
Is Nemotron 3.5 Bolt 74B-A9B better than Ling 3.0 Flash VL?›
On AutomationBench-AA, Nemotron 3.5 Bolt 74B-A9B scores 15.5 vs 15.7 — about the same.
What is the context window of Nemotron 3.5 Bolt 74B-A9B?›
256K tokens.
When was Nemotron 3.5 Bolt 74B-A9B released? Is there a newer version?›
Released 2026-10-15. It is the current version in its line.
Is Nemotron 3.5 Bolt 74B-A9B open source?›
Yes, the weights are open (openmdw-1.1 licence).
Can I run Nemotron 3.5 Bolt 74B-A9B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Nemotron 3.5 Bolt 74B-A9B read images?›
It accepts text and images as input.
What is Nemotron 3.5 Bolt 74B-A9B?›
Nemotron 3.5 Bolt 74B-A9B is an open-weights language model from NVIDIA, released Oct 2026.
What are the best alternatives to Nemotron 3.5 Bolt 74B-A9B?›
GPT-5.6 Luna (better), Qwen3.8 Flash (open weights).