Nemotron 3.5 Bolt 74B-A9B
Oct 2026
Nemotron 3.5 Bolt 74B-A9BCompare inon
Benchmarks of Nemotron 3.5 Bolt 74B-A9B13
BenchmarkByScoreRank
Overall1
Knowledge3
Science3
Coding1
Agents3
Documents2
No benchmark matches
—per task?
self-host onlyprice
—output speed?
256Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.6 Lunamedium+17%—$0.016
OpenQwen3.8 Flashthinking+86%—$0.37Memory (4-bit): 45 GB → 108 GB+6BetterGPT-6 Lunamedium+40%—$0.017Function calling only with none · Chat Completions+3
BetterClaude Haiku 5.5low+38%—$0.024Remove sampling parameters+5
BetterMiMo v2.5 ProthinkingOpen+21%—$0.054Memory (4-bit): 45 GB → 614 GB+1ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5.6 Lunamedium+17%—$0.016GPT-6 Lunamedium+40%—$0.017Function calling only with none · Chat Completions+3Claude Haiku 5.5low+38%—$0.024Remove sampling parameters+5MiMo v2.5 ProthinkingOpen+21%—$0.054Memory (4-bit): 45 GB → 614 GB+1MiMo v2.6 FlashthinkingOpen+77%—$0.062Memory (4-bit): 45 GB → 186 GB+4ModelScoreCostPer taskWhat changes
Qwen3.8 FlashthinkingOpen+86%—$0.37Memory (4-bit): 45 GB → 108 GB+6Qwen3.8 27BxhighOpen+57%—$1.01max_tokens range · QwenCloud+4Nemotron 3.5 Super VLOpen+24%—$0.19Memory (4-bit): 45 GB → 75 GBIK2 Horizon MoVA 36B A4BthinkingOpen+18%—$1 / $4No image input
Ling 3.0 Flash VLthinkingOpen+15%—$0.06 / $0.18Memory (4-bit): 45 GB → 75 GBModelScoreCostPer taskWhat changes
Nemotron 3.5 Super VLOpen+24%—$0.19Memory (4-bit): 45 GB → 75 GBNemotron 3 UltrathinkingOpen+7%—$0.58Memory (4-bit): 45 GB → 336 GB+1Nemotron 3.5 LightningthinkingOpen-40%—$0.079No image inputNemotron 3 Super 120B A12BOpen-40%—$1.64Memory (4-bit): 45 GB → 74 GB+1Nemotron Cascade 2 30B A3BOpen-45%——No image inputNemotron 3 Nano Omni 30B A3B ReasoningOpen-52%—$0 / $0Llama Nemotron Super 49B v1.5non-thinkingOpen-66%—$0.40 / $0.40Context: 256K → 128K+1Llama 3.1 Nemotron Nano 4B v1.1Open-66%——Context: 256K → 128K+1All 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
all categoriesChat & Knowledge
Humanity's Last Exam24.7#101
AA Omniscience Index-19.2#122
CritPt (physics)4.3#86
AA Intelligence Index 4.3.221.4#112
AA Omniscience · Accuracy17.1#200
AA-LCR (long context) 1.169.7#126
GDP.pdf · AA all-pass2.8#102
Coding
SciCode39.7#97
Agents & Tool Use
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 Qwen3.6 27B?›
On AA Intelligence Index 4.3.2, Nemotron 3.5 Bolt 74B-A9B scores 21.4 vs 21.4 — 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).