Llama 3.1 Nemotron Nano 4B v1.1
May 2025
Llama 3.1 Nemotron Nano 4B v1.1Compare inon
Benchmarks of Llama 3.1 Nemotron Nano 4B v1.18
BenchmarkByScoreRank
Overall1
Knowledge1
Science1
Documents1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
self-host onlyprice
—output speed?
128Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT OSS 20BhighOpen+79%—$0.011Memory (4-bit): 2.3 GB → 13 GB
OpenQwen3 4B 2507 (Reasoning)+65%—$0.40 / $0.80BetterNemotron 3 Nano 30B A3BthinkingOpen+82%—$0.017Memory (4-bit): 2.3 GB → 19 GBBetterGPT-5 Minihigh+81%—$0.053BetterQwen3 30B A3B 2507 (Reasoning)thinkingOpen+13%—$0.066Memory (4-bit): 2.3 GB → 18 GBModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT OSS 20BhighOpen+79%—$0.011Memory (4-bit): 2.3 GB → 13 GBNemotron 3 Nano 30B A3BthinkingOpen+82%—$0.017Memory (4-bit): 2.3 GB → 19 GBGPT-5 Minihigh+81%—$0.053Qwen3 30B A3B 2507 (Reasoning)thinkingOpen+13%—$0.066Memory (4-bit): 2.3 GB → 18 GBQwen3 235B A22B Thinking 2507thinkingOpen+82%—$0.08Memory (4-bit): 2.3 GB → 141 GB+1ModelScoreCostPer taskWhat changes
Qwen3 4B 2507 (Reasoning)Open+65%—$0.40 / $0.80TFalcon H1R 7BthinkingOpen+60%——Memory (4-bit): 2.3 GB → 3.8 GBNVIDIA Nemotron Nano 12B v2 VLthinkingOpen+50%—$0.20 / $0.60Memory (4-bit): 2.3 GB → 6.6 GB
Olmo 3 7B ThinkOpen+41%——Context: 128K → 66K+1NVIDIA Nemotron Nano 9B V2thinkingOpen+39%—$0.04 / $0.16Memory (4-bit): 2.3 GB → 4.4 GBModelScoreCostPer taskWhat changes
NVIDIA Nemotron Nano 9B V2non-thinkingOpen+25%—$0.04 / $0.16Memory (4-bit): 2.3 GB → 4.4 GBNVIDIA Nemotron Nano 12B v2 VLnon-thinkingOpen-47%—$0.20 / $0.60Memory (4-bit): 2.3 GB → 6.6 GBNemotron 3 Nano 30B A3Bnon-thinkingOpen-73%—$0.06 / $0.24Memory (4-bit): 2.3 GB → 19 GBLlama Nemotron Super 49B v1.5non-thinkingOpen-84%—$0.40 / $0.40Memory (4-bit): 2.3 GB → 30 GBNVIDIA Nemotron Labs Dory 1.0 4BOpenn/a——Memory (4-bit): 2.3 GB → 2.4 GBNemotron 3.5 Super VLthinkingOpenn/a—$0.19Memory (4-bit): 2.3 GB → 75 GBNemotron 3.5 Bolt 74B-A9BOpenn/a——Memory (4-bit): 2.3 GB → 45 GBNVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4Openn/a—$0.08 / $0.45Memory (4-bit): not verifiedAll NVIDIA models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
Licencenvidia-open-model-licensecommercial use with conditions
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam5.2#270
AA Intelligence Index 4.3.2≈7.3#272
GPQA Diamond40.8#281
Coding
LiveCodeBench · AA archived49.3#91
Agents & Tool Use
τ²-bench · AA11.7#223
Writing & Language
IFBench (instructions)25.5#230
FAQ
How much does Llama 3.1 Nemotron Nano 4B v1.1 cost?›
There is no per-unit API price: self-host only.
Is Llama 3.1 Nemotron Nano 4B v1.1 free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Llama 3.1 Nemotron Nano 4B v1.1, and what is it best at?›
#268 of 336 in Chat & Knowledge, #91 of 152 in Coding, #220 of 242 in Agents & Tool Use, #227 of 245 in Writing & Language.
Is Llama 3.1 Nemotron Nano 4B v1.1 better than Exaone 4.0 1.2B?›
On AIME 2025 · AA archived, Llama 3.1 Nemotron Nano 4B v1.1 scores 50 vs 50.3 — about the same.
What is the context window of Llama 3.1 Nemotron Nano 4B v1.1?›
128K tokens.
When was Llama 3.1 Nemotron Nano 4B v1.1 released? Is there a newer version?›
Released 2025-05-20. It has been superseded by NVIDIA Nemotron 3 Nano 4B.
Is Llama 3.1 Nemotron Nano 4B v1.1 open source?›
Yes, the weights are open (nvidia-open-model-license licence).
Can I run Llama 3.1 Nemotron Nano 4B v1.1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Llama 3.1 Nemotron Nano 4B v1.1 read images?›
No, it accepts text only.
What is Llama 3.1 Nemotron Nano 4B v1.1?›
Llama 3.1 Nemotron Nano 4B v1.1 is an open-weights language model from NVIDIA, released May 2025.
What are the best alternatives to Llama 3.1 Nemotron Nano 4B v1.1?›
GPT OSS 20B (better), Qwen3 4B 2507 (Reasoning) (open weights).