LG AI Research · lgai-exaone/exaone-4-0-1-2b
| Provider | LG AI Research |
|---|---|
| Family | exaone |
| Type | llm-chat |
| Status | active |
| Released | 2025-07-11 |
| Updated | 2025-08-04 |
| Parameters | 1.3B |
| Open weights | yes |
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 | 2.56 GB | ~5744918.6 | ~22979674.5 q4 |
| NVIDIA GB200 Grace Blackwell Superchip | 372.0 GB | 16000.0 GB/s | bf16 | 2.56 GB | ~4377.1 | ~17508.3 q4 |
| AMD Instinct MI355X | 288.0 GB | 8000.0 GB/s | bf16 | 2.56 GB | ~2188.5 | ~8754.2 q4 |
| NVIDIA B200 | 180.0 GB | 7700.0 GB/s | bf16 | 2.56 GB | ~2106.5 | ~8425.9 q4 |
| Google TPU7x (Ironwood) | 192.0 GB | 7380.0 GB/s | bf16 | 2.56 GB | ~2018.9 | ~8075.7 q4 |
| AMD Instinct MI325X | 256.0 GB | 6000.0 GB/s | bf16 | 2.56 GB | ~1641.4 | ~6565.6 q4 |
| AMD Instinct MI300X | 192.0 GB | 5300.0 GB/s | bf16 | 2.56 GB | ~1449.9 | ~5799.6 q4 |
| NVIDIA H200 SXM | 141.0 GB | 4800.0 GB/s | bf16 | 2.56 GB | ~1313.1 | ~5252.5 q4 |
| NVIDIA H100 NVL | 94.0 GB | 3900.0 GB/s | bf16 | 2.56 GB | ~1066.9 | ~4267.7 q4 |
| NVIDIA H100 SXM | 80.0 GB | 3350.0 GB/s | bf16 | 2.56 GB | ~916.5 | ~3665.8 q4 |
| AMD Instinct MI250X | 128.0 GB | 3200.0 GB/s | bf16 | 2.56 GB | ~875.4 | ~3501.7 q4 |
| Google TPU v5p | 95.0 GB | 2765.0 GB/s | bf16 | 2.56 GB | ~756.4 | ~3025.7 q4 |
| NVIDIA A100 80GB SXM | 80.0 GB | 2039.0 GB/s | bf16 | 2.56 GB | ~557.8 | ~2231.2 q4 |
| NVIDIA H100 PCIe | 80.0 GB | 2000.0 GB/s | bf16 | 2.56 GB | ~547.1 | ~2188.5 q4 |
| NVIDIA GeForce RTX 5090 | 32.0 GB | 1792.0 GB/s | bf16 | 2.56 GB | ~490.2 | ~1960.9 q4 |
| Google TPU v6e (Trillium) | 32.0 GB | 1638.0 GB/s | bf16 | 2.56 GB | ~448.1 | ~1792.4 q4 |
| AMD Instinct MI210 | 64.0 GB | 1600.0 GB/s | bf16 | 2.56 GB | ~437.7 | ~1750.8 q4 |
| NVIDIA A100 40GB SXM | 40.0 GB | 1555.0 GB/s | bf16 | 2.56 GB | ~425.4 | ~1701.6 q4 |
| Google TPU v4 | 32.0 GB | 1200.0 GB/s | bf16 | 2.56 GB | ~328.3 | ~1313.1 q4 |
| NVIDIA GeForce RTX 4090 | 24.0 GB | 1008.0 GB/s | bf16 | 2.56 GB | ~275.8 | ~1103.0 q4 |
| AMD Radeon RX 7900 XTX | 24.0 GB | 960.0 GB/s | bf16 | 2.56 GB | ~262.6 | ~1050.5 q4 |
| NVIDIA GeForce RTX 5080 | 16.0 GB | 960.0 GB/s | bf16 | 2.56 GB | ~262.6 | ~1050.5 q4 |
| NVIDIA GeForce RTX 3090 | 24.0 GB | 936.0 GB/s | bf16 | 2.56 GB | ~256.1 | ~1024.2 q4 |
| NVIDIA L40S | 48.0 GB | 864.0 GB/s | bf16 | 2.56 GB | ~236.4 | ~945.4 q4 |
| Apple M3 Ultra | 512.0 GB | 819.0 GB/s | bf16 | 2.56 GB | ~224.1 | ~896.2 q4 |
| AMD Radeon RX 7900 XT | 20.0 GB | 800.0 GB/s | bf16 | 2.56 GB | ~218.9 | ~875.4 q4 |
| Apple M2 Ultra | 192.0 GB | 800.0 GB/s | bf16 | 2.56 GB | ~218.9 | ~875.4 q4 |
| Google TPU v5e | 16.0 GB | 800.0 GB/s | bf16 | 2.56 GB | ~218.9 | ~875.4 q4 |
| NVIDIA GeForce RTX 4080 SUPER | 16.0 GB | 736.0 GB/s | bf16 | 2.56 GB | ~201.3 | ~805.4 q4 |
| NVIDIA GeForce RTX 4070 Ti SUPER | 16.0 GB | 672.0 GB/s | bf16 | 2.56 GB | ~183.8 | ~735.3 q4 |
| AMD Radeon RX 9070 XT | 16.0 GB | 640.0 GB/s | bf16 | 2.56 GB | ~175.1 | ~700.3 q4 |
| Apple M4 Max | 128.0 GB | 546.0 GB/s | bf16 | 2.56 GB | ~149.4 | ~597.5 q4 |
| Apple M1 Max | 64.0 GB | 400.0 GB/s | bf16 | 2.56 GB | ~109.4 | ~437.7 q4 |
| Apple M2 Max | 96.0 GB | 400.0 GB/s | bf16 | 2.56 GB | ~109.4 | ~437.7 q4 |
| Apple M3 Max | 128.0 GB | 400.0 GB/s | bf16 | 2.56 GB | ~109.4 | ~437.7 q4 |
| NVIDIA GeForce RTX 3060 12GB | 12.0 GB | 360.0 GB/s | bf16 | 2.56 GB | ~98.5 | ~393.9 q4 |
| NVIDIA L4 | 24.0 GB | 300.0 GB/s | bf16 | 2.56 GB | ~82.1 | ~328.3 q4 |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16.0 GB | 288.0 GB/s | bf16 | 2.56 GB | ~78.8 | ~315.1 q4 |
| Apple M4 Pro | 64.0 GB | 273.0 GB/s | bf16 | 2.56 GB | ~74.7 | ~298.7 q4 |
| Apple M4 | 32.0 GB | 120.0 GB/s | bf16 | 2.56 GB | ~32.8 | ~131.3 q4 |
Taken from the card's availability section.
| Platform | Id on that platform |
|---|---|
| Hugging Face | LGAI-EXAONE/EXAONE-4.0-1.2B |
| Benchmark | Evaluated as | Score | Evidence date | Source kind | |
|---|---|---|---|---|---|
| aa_lcr | Exaone 4.0 1.2B | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| critpt | Exaone 4.0 1.2B | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| gpqa_diamond | Exaone 4.0 1.2B | 51.52% | 2026-09-10 evaluated | independent evaluator | source |
This card reports no benchmark scores yet.
| Benchmark | Catalogue standing | Score |
|---|