Liquid AI · liquid/lfm2-2-6b
| Provider | Liquid AI |
|---|---|
| Family | lfm2 |
| Type | llm-chat |
| Status | active |
| Released | 2025-09-22 |
| Updated | 2026-08-05 |
| Parameters | 2.6B |
| 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 | 5.14 GB | ~2860732.2 | ~11442928.7 q4 |
| NVIDIA GB200 Grace Blackwell Superchip | 372.0 GB | 16000.0 GB/s | bf16 | 5.14 GB | ~2179.6 | ~8718.4 q4 |
| AMD Instinct MI355X | 288.0 GB | 8000.0 GB/s | bf16 | 5.14 GB | ~1089.8 | ~4359.2 q4 |
| NVIDIA B200 | 180.0 GB | 7700.0 GB/s | bf16 | 5.14 GB | ~1048.9 | ~4195.7 q4 |
| Google TPU7x (Ironwood) | 192.0 GB | 7380.0 GB/s | bf16 | 5.14 GB | ~1005.3 | ~4021.4 q4 |
| AMD Instinct MI325X | 256.0 GB | 6000.0 GB/s | bf16 | 5.14 GB | ~817.4 | ~3269.4 q4 |
| AMD Instinct MI300X | 192.0 GB | 5300.0 GB/s | bf16 | 5.14 GB | ~722.0 | ~2888.0 q4 |
| NVIDIA H200 SXM | 141.0 GB | 4800.0 GB/s | bf16 | 5.14 GB | ~653.9 | ~2615.5 q4 |
| NVIDIA H100 NVL | 94.0 GB | 3900.0 GB/s | bf16 | 5.14 GB | ~531.3 | ~2125.1 q4 |
| NVIDIA H100 SXM | 80.0 GB | 3350.0 GB/s | bf16 | 5.14 GB | ~456.4 | ~1825.4 q4 |
| AMD Instinct MI250X | 128.0 GB | 3200.0 GB/s | bf16 | 5.14 GB | ~435.9 | ~1743.7 q4 |
| Google TPU v5p | 95.0 GB | 2765.0 GB/s | bf16 | 5.14 GB | ~376.7 | ~1506.7 q4 |
| NVIDIA A100 80GB SXM | 80.0 GB | 2039.0 GB/s | bf16 | 5.14 GB | ~277.8 | ~1111.1 q4 |
| NVIDIA H100 PCIe | 80.0 GB | 2000.0 GB/s | bf16 | 5.14 GB | ~272.5 | ~1089.8 q4 |
| NVIDIA GeForce RTX 5090 | 32.0 GB | 1792.0 GB/s | bf16 | 5.14 GB | ~244.1 | ~976.5 q4 |
| Google TPU v6e (Trillium) | 32.0 GB | 1638.0 GB/s | bf16 | 5.14 GB | ~223.1 | ~892.5 q4 |
| AMD Instinct MI210 | 64.0 GB | 1600.0 GB/s | bf16 | 5.14 GB | ~218.0 | ~871.8 q4 |
| NVIDIA A100 40GB SXM | 40.0 GB | 1555.0 GB/s | bf16 | 5.14 GB | ~211.8 | ~847.3 q4 |
| Google TPU v4 | 32.0 GB | 1200.0 GB/s | bf16 | 5.14 GB | ~163.5 | ~653.9 q4 |
| NVIDIA GeForce RTX 4090 | 24.0 GB | 1008.0 GB/s | bf16 | 5.14 GB | ~137.3 | ~549.3 q4 |
| AMD Radeon RX 7900 XTX | 24.0 GB | 960.0 GB/s | bf16 | 5.14 GB | ~130.8 | ~523.1 q4 |
| NVIDIA GeForce RTX 5080 | 16.0 GB | 960.0 GB/s | bf16 | 5.14 GB | ~130.8 | ~523.1 q4 |
| NVIDIA GeForce RTX 3090 | 24.0 GB | 936.0 GB/s | bf16 | 5.14 GB | ~127.5 | ~510.0 q4 |
| NVIDIA L40S | 48.0 GB | 864.0 GB/s | bf16 | 5.14 GB | ~117.7 | ~470.8 q4 |
| Apple M3 Ultra | 512.0 GB | 819.0 GB/s | bf16 | 5.14 GB | ~111.6 | ~446.3 q4 |
| AMD Radeon RX 7900 XT | 20.0 GB | 800.0 GB/s | bf16 | 5.14 GB | ~109.0 | ~435.9 q4 |
| Apple M2 Ultra | 192.0 GB | 800.0 GB/s | bf16 | 5.14 GB | ~109.0 | ~435.9 q4 |
| Google TPU v5e | 16.0 GB | 800.0 GB/s | bf16 | 5.14 GB | ~109.0 | ~435.9 q4 |
| NVIDIA GeForce RTX 4080 SUPER | 16.0 GB | 736.0 GB/s | bf16 | 5.14 GB | ~100.3 | ~401.0 q4 |
| NVIDIA GeForce RTX 4070 Ti SUPER | 16.0 GB | 672.0 GB/s | bf16 | 5.14 GB | ~91.5 | ~366.2 q4 |
| AMD Radeon RX 9070 XT | 16.0 GB | 640.0 GB/s | bf16 | 5.14 GB | ~87.2 | ~348.7 q4 |
| Apple M4 Max | 128.0 GB | 546.0 GB/s | bf16 | 5.14 GB | ~74.4 | ~297.5 q4 |
| Apple M1 Max | 64.0 GB | 400.0 GB/s | bf16 | 5.14 GB | ~54.5 | ~218.0 q4 |
| Apple M2 Max | 96.0 GB | 400.0 GB/s | bf16 | 5.14 GB | ~54.5 | ~218.0 q4 |
| Apple M3 Max | 128.0 GB | 400.0 GB/s | bf16 | 5.14 GB | ~54.5 | ~218.0 q4 |
| NVIDIA GeForce RTX 3060 12GB | 12.0 GB | 360.0 GB/s | bf16 | 5.14 GB | ~49.0 | ~196.2 q4 |
| NVIDIA L4 | 24.0 GB | 300.0 GB/s | bf16 | 5.14 GB | ~40.9 | ~163.5 q4 |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16.0 GB | 288.0 GB/s | bf16 | 5.14 GB | ~39.2 | ~156.9 q4 |
| Apple M4 Pro | 64.0 GB | 273.0 GB/s | bf16 | 5.14 GB | ~37.2 | ~148.8 q4 |
| Apple M4 | 32.0 GB | 120.0 GB/s | bf16 | 5.14 GB | ~16.3 | ~65.4 q4 |
Taken from the card's availability section.
| Platform | Id on that platform |
|---|---|
| Hugging Face | LiquidAI/LFM2-2.6B |
| Benchmark | Evaluated as | Score | Evidence date | Source kind | |
|---|---|---|---|---|---|
| aa_lcr | LFM2 2.6B | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| critpt | LFM2 2.6B | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| gpqa_diamond | LFM2 2.6B | 30.61% | 2026-09-10 evaluated | independent evaluator | source |
This card reports no benchmark scores yet.
| Benchmark | Catalogue standing | Score |
|---|