Nemotron 3.5 Bolt 74B-A9B
Oct 2026
Nemotron 3.5 Bolt 74B-A9BCompare inon
Nemotron 3.5 Bolt 74B-A9B measured on 2 of 28 Coding benchmarks2
BenchmarkByScoreRank
Coding1
Agents1
No benchmark matches
—per task?
self-host onlyprice
—output speed?
256Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunamedium+2.5—$0.017Function calling only with none · Chat Completions+3
OpenQwen3.8 Flashthinking+25.3—$0.37Memory (4-bit): 45 GB → 108 GB+6
BetterClaude Haiku 5.5low+12.6—$0.024Remove sampling parameters+5BetterGPT-5.6 Lunahigh+2.5—$0.044
BetterMiMo v2.6 FlashthinkingOpen+22.7—$0.062Memory (4-bit): 45 GB → 186 GB+4ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunamedium+2.5—$0.017Function calling only with none · Chat Completions+3Claude Haiku 5.5low+12.6—$0.024Remove sampling parameters+5GPT-5.6 Lunahigh+2.5—$0.044MiMo v2.6 FlashthinkingOpen+22.7—$0.062Memory (4-bit): 45 GB → 186 GB+4GPT-6.1 Sollow+30.8—$0.13Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
Qwen3.8 FlashthinkingOpen+25.3—$0.37Memory (4-bit): 45 GB → 108 GB+6Qwen3.8 27BxhighOpen+5.6—$1.01max_tokens range · QwenCloud+4IK2 Horizon 7BthinkingOpen+1—$0.30 / $1.20No image input
North Mini CodeOpensame——No image input
Muse Glimmer 30BhighOpensame—$0.058Context: 256K → 131KModelScoreCostPer taskWhat changes
Nemotron 3.5 LightningthinkingOpensame—$0.079No image inputNemotron 3 UltrathinkingOpensame—$0.58Memory (4-bit): 45 GB → 336 GB+1Nemotron 3.5 Super VLOpensame—$0.19Memory (4-bit): 45 GB → 75 GBNVIDIA Nemotron 3 Nano 4BOpensame——No image inputNemotron 3 Super 120B A12BOpensame—$1.64Memory (4-bit): 45 GB → 74 GB+1Nemotron 3 Nano 30B A3BthinkingOpensame—$0.017Context: 256K → 131K+1NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4Openn/a—$0.08 / $0.45Memory (4-bit): not verifiedNemotron 3 Nano Omni 30B A3B ReasoningOpenn/a—$0 / $0All 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
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 Mistral Large 3?›
On Terminal-Bench 4.0, Nemotron 3.5 Bolt 74B-A9B scores 0 vs 0 — 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-6 Luna (better), Qwen3.8 Flash (open weights).