NVIDIA · nvidia/llama-3-1-nemotron-nano-4b-v1-1
| Provider | NVIDIA |
|---|---|
| Family | llama-nemotron |
| Type | llm-chat |
| Status | active |
| Released | 2025-05-03 |
| Updated | 2025-10-15 |
| Parameters | 4.5B |
| Open weights | yes |
| Relationship | Model |
|---|---|
| Is a finetune of | nvidia/Llama-3.1-Minitron-4B-Width-Base |
Ordered by predicted speed. Bandwidth sets decode rate; memory decides whether it runs at all.
| Device | Memory | Bandwidth | Best quality | Weights | tok/s | Fastest |
|---|---|---|---|---|---|---|
| Cerebras WSE-3 | 44.0 GB | 21000000.0 GB/s | bf16 | 9.03 GB | ~1628719.9 | ~6514879.6 q4 |
| NVIDIA GB200 Grace Blackwell Superchip | 372.0 GB | 16000.0 GB/s | bf16 | 9.03 GB | ~1240.9 | ~4963.7 q4 |
| AMD Instinct MI355X | 288.0 GB | 8000.0 GB/s | bf16 | 9.03 GB | ~620.5 | ~2481.9 q4 |
| NVIDIA B200 | 180.0 GB | 7700.0 GB/s | bf16 | 9.03 GB | ~597.2 | ~2388.8 q4 |
| Google TPU7x (Ironwood) | 192.0 GB | 7380.0 GB/s | bf16 | 9.03 GB | ~572.4 | ~2289.5 q4 |
| AMD Instinct MI325X | 256.0 GB | 6000.0 GB/s | bf16 | 9.03 GB | ~465.3 | ~1861.4 q4 |
| AMD Instinct MI300X | 192.0 GB | 5300.0 GB/s | bf16 | 9.03 GB | ~411.1 | ~1644.2 q4 |
| NVIDIA H200 SXM | 141.0 GB | 4800.0 GB/s | bf16 | 9.03 GB | ~372.3 | ~1489.1 q4 |
| NVIDIA H100 NVL | 94.0 GB | 3900.0 GB/s | bf16 | 9.03 GB | ~302.5 | ~1209.9 q4 |
| NVIDIA H100 SXM | 80.0 GB | 3350.0 GB/s | bf16 | 9.03 GB | ~259.8 | ~1039.3 q4 |
| AMD Instinct MI250X | 128.0 GB | 3200.0 GB/s | bf16 | 9.03 GB | ~248.2 | ~992.7 q4 |
| Google TPU v5p | 95.0 GB | 2765.0 GB/s | bf16 | 9.03 GB | ~214.4 | ~857.8 q4 |
| NVIDIA A100 80GB SXM | 80.0 GB | 2039.0 GB/s | bf16 | 9.03 GB | ~158.1 | ~632.6 q4 |
| NVIDIA H100 PCIe | 80.0 GB | 2000.0 GB/s | bf16 | 9.03 GB | ~155.1 | ~620.5 q4 |
| NVIDIA GeForce RTX 5090 | 32.0 GB | 1792.0 GB/s | bf16 | 9.03 GB | ~139.0 | ~555.9 q4 |
| Google TPU v6e (Trillium) | 32.0 GB | 1638.0 GB/s | bf16 | 9.03 GB | ~127.0 | ~508.2 q4 |
| AMD Instinct MI210 | 64.0 GB | 1600.0 GB/s | bf16 | 9.03 GB | ~124.1 | ~496.4 q4 |
| NVIDIA A100 40GB SXM | 40.0 GB | 1555.0 GB/s | bf16 | 9.03 GB | ~120.6 | ~482.4 q4 |
| Google TPU v4 | 32.0 GB | 1200.0 GB/s | bf16 | 9.03 GB | ~93.1 | ~372.3 q4 |
| NVIDIA GeForce RTX 4090 | 24.0 GB | 1008.0 GB/s | bf16 | 9.03 GB | ~78.2 | ~312.7 q4 |
| AMD Radeon RX 7900 XTX | 24.0 GB | 960.0 GB/s | bf16 | 9.03 GB | ~74.5 | ~297.8 q4 |
| NVIDIA GeForce RTX 5080 | 16.0 GB | 960.0 GB/s | bf16 | 9.03 GB | ~74.5 | ~297.8 q4 |
| NVIDIA GeForce RTX 3090 | 24.0 GB | 936.0 GB/s | bf16 | 9.03 GB | ~72.6 | ~290.4 q4 |
| NVIDIA L40S | 48.0 GB | 864.0 GB/s | bf16 | 9.03 GB | ~67.0 | ~268.0 q4 |
| Apple M3 Ultra | 512.0 GB | 819.0 GB/s | bf16 | 9.03 GB | ~63.5 | ~254.1 q4 |
| AMD Radeon RX 7900 XT | 20.0 GB | 800.0 GB/s | bf16 | 9.03 GB | ~62.0 | ~248.2 q4 |
| Apple M2 Ultra | 192.0 GB | 800.0 GB/s | bf16 | 9.03 GB | ~62.0 | ~248.2 q4 |
| Google TPU v5e | 16.0 GB | 800.0 GB/s | bf16 | 9.03 GB | ~62.0 | ~248.2 q4 |
| NVIDIA GeForce RTX 4080 SUPER | 16.0 GB | 736.0 GB/s | bf16 | 9.03 GB | ~57.1 | ~228.3 q4 |
| NVIDIA GeForce RTX 4070 Ti SUPER | 16.0 GB | 672.0 GB/s | bf16 | 9.03 GB | ~52.1 | ~208.5 q4 |
| AMD Radeon RX 9070 XT | 16.0 GB | 640.0 GB/s | bf16 | 9.03 GB | ~49.6 | ~198.5 q4 |
| Apple M4 Max | 128.0 GB | 546.0 GB/s | bf16 | 9.03 GB | ~42.3 | ~169.4 q4 |
| Apple M1 Max | 64.0 GB | 400.0 GB/s | bf16 | 9.03 GB | ~31.0 | ~124.1 q4 |
| Apple M2 Max | 96.0 GB | 400.0 GB/s | bf16 | 9.03 GB | ~31.0 | ~124.1 q4 |
| Apple M3 Max | 128.0 GB | 400.0 GB/s | bf16 | 9.03 GB | ~31.0 | ~124.1 q4 |
| NVIDIA GeForce RTX 3060 12GB | 12.0 GB | 360.0 GB/s | fp8 | 4.51 GB | ~55.8 | ~111.7 q4 |
| NVIDIA L4 | 24.0 GB | 300.0 GB/s | bf16 | 9.03 GB | ~23.3 | ~93.1 q4 |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16.0 GB | 288.0 GB/s | bf16 | 9.03 GB | ~22.3 | ~89.3 q4 |
| Apple M4 Pro | 64.0 GB | 273.0 GB/s | bf16 | 9.03 GB | ~21.2 | ~84.7 q4 |
| Apple M4 | 32.0 GB | 120.0 GB/s | bf16 | 9.03 GB | ~9.3 | ~37.2 q4 |
Taken from the card's availability section.
| Platform | Id on that platform |
|---|---|
| Hugging Face | nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 |
| Benchmark | Evaluated as | Score | Evidence date | Source kind | |
|---|---|---|---|---|---|
| aa_lcr | Llama 3.1 Nemotron Nano 4B v1.1 | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| gpqa_diamond | Llama 3.1 Nemotron Nano 4B v1.1 | 40.81% | 2026-09-10 evaluated | independent evaluator | source |
This card reports no benchmark scores yet.
| Benchmark | Catalogue standing | Score |
|---|