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-6 Lunalow×2.9—$0.005Function calling only with none · Chat Completions+3IOpenK2 Horizon 7Bthinking×2.8—$0.30 / $1.20Memory (4-bit): 2.3 GB → 4.5 GBBetterGPT-5.6 Lunalow×2.9—$0.01
BetterMistral Small 4thinkingOpen+54%—$0.015Memory (4-bit): 2.3 GB → 72 GB
BetterMiMo v2.5thinkingOpen×3—$0.019Memory (4-bit): 2.3 GB → 186 GBModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×2.9—$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2.9—$0.01Mistral Small 4thinkingOpen+54%—$0.015Memory (4-bit): 2.3 GB → 72 GBMiMo v2.5thinkingOpen×3—$0.019Memory (4-bit): 2.3 GB → 186 GB
DeepSeek V3 0324non-thinkingOpen+33%—$0.021Memory (4-bit): 2.3 GB → 411 GBModelScoreCostPer taskWhat changes
IK2 Horizon 7BthinkingOpen×2.8—$0.30 / $1.20Memory (4-bit): 2.3 GB → 4.5 GBIK2 Horizon 3.7BthinkingOpen×2.1—$0.30 / $1.20Memory (4-bit): 2.3 GB → 2.5 GB
Gemma 4 12BthinkingOpen+94%—$0.10 / $0.30Memory (4-bit): 2.3 GB → 6 GB
Qwen 3.5 9Bnon-thinkingOpen+82%—$0.08 / $0.13Memory (4-bit): 2.3 GB → 4.8 GBQwen3.5 4BthinkingOpen+80%—$0.03 / $0.15ModelScoreCostPer taskWhat changes
Nemotron 3.5 Super VLOpen×3.6—$0.19Memory (4-bit): 2.3 GB → 75 GBNemotron 3 UltrathinkingOpen×3.1—$0.58Memory (4-bit): 2.3 GB → 336 GBNemotron 3.5 Bolt 74B-A9BOpen×2.9——Memory (4-bit): 2.3 GB → 45 GBNemotron 3.5 LightningthinkingOpen+76%—$0.079Memory (4-bit): 2.3 GB → 20 GBNemotron 3 Super 120B A12BOpen+76%—$1.64Memory (4-bit): 2.3 GB → 74 GBNemotron Cascade 2 30B A3BOpen+60%——Memory (4-bit): 2.3 GB → 19 GBNemotron 3 Nano Omni 30B A3B ReasoningOpen+40%—$0 / $0Memory (4-bit): 2.3 GB → 20 GBLlama Nemotron Super 49B v1.5non-thinkingOpensame—$0.40 / $0.40Memory (4-bit): 2.3 GB → 30 GBAll 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#268
AA Intelligence Index 4.3.2≈7.3#270
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?›
#266 of 334 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 GPT-4o (2024-05-13)?›
On AA Intelligence Index 4.3.2, Llama 3.1 Nemotron Nano 4B v1.1 scores 7.3 vs 7.3 — 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-6 Luna (better), K2 Horizon 7B (open weights).