Liquid AI · liquid/lfm2-5-8b-a1b
| Provider | Liquid AI |
|---|---|
| Family | lfm2 |
| Type | llm-chat |
| Status | active |
| Released | 2026-05-28 |
| Updated | 2026-08-24 |
| Parameters | 8.5B |
| Open weights | yes |
| Relationship | Model |
|---|---|
| Is a finetune of | LiquidAI/LFM2.5-8B-A1B-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 | 16.94 GB | ~867988.2 | ~3471952.9 q4 |
| NVIDIA GB200 Grace Blackwell Superchip | 372.0 GB | 16000.0 GB/s | bf16 | 16.94 GB | ~661.3 | ~2645.3 q4 |
| AMD Instinct MI355X | 288.0 GB | 8000.0 GB/s | bf16 | 16.94 GB | ~330.7 | ~1322.6 q4 |
| NVIDIA B200 | 180.0 GB | 7700.0 GB/s | bf16 | 16.94 GB | ~318.3 | ~1273.0 q4 |
| Google TPU7x (Ironwood) | 192.0 GB | 7380.0 GB/s | bf16 | 16.94 GB | ~305.0 | ~1220.1 q4 |
| AMD Instinct MI325X | 256.0 GB | 6000.0 GB/s | bf16 | 16.94 GB | ~248.0 | ~992.0 q4 |
| AMD Instinct MI300X | 192.0 GB | 5300.0 GB/s | bf16 | 16.94 GB | ~219.1 | ~876.3 q4 |
| NVIDIA H200 SXM | 141.0 GB | 4800.0 GB/s | bf16 | 16.94 GB | ~198.4 | ~793.6 q4 |
| NVIDIA H100 NVL | 94.0 GB | 3900.0 GB/s | bf16 | 16.94 GB | ~161.2 | ~644.8 q4 |
| NVIDIA H100 SXM | 80.0 GB | 3350.0 GB/s | bf16 | 16.94 GB | ~138.5 | ~553.9 q4 |
| AMD Instinct MI250X | 128.0 GB | 3200.0 GB/s | bf16 | 16.94 GB | ~132.3 | ~529.1 q4 |
| Google TPU v5p | 95.0 GB | 2765.0 GB/s | bf16 | 16.94 GB | ~114.3 | ~457.1 q4 |
| NVIDIA A100 80GB SXM | 80.0 GB | 2039.0 GB/s | bf16 | 16.94 GB | ~84.3 | ~337.1 q4 |
| NVIDIA H100 PCIe | 80.0 GB | 2000.0 GB/s | bf16 | 16.94 GB | ~82.7 | ~330.7 q4 |
| NVIDIA GeForce RTX 5090 | 32.0 GB | 1792.0 GB/s | bf16 | 16.94 GB | ~74.1 | ~296.3 q4 |
| Google TPU v6e (Trillium) | 32.0 GB | 1638.0 GB/s | bf16 | 16.94 GB | ~67.7 | ~270.8 q4 |
| AMD Instinct MI210 | 64.0 GB | 1600.0 GB/s | bf16 | 16.94 GB | ~66.1 | ~264.5 q4 |
| NVIDIA A100 40GB SXM | 40.0 GB | 1555.0 GB/s | bf16 | 16.94 GB | ~64.3 | ~257.1 q4 |
| Google TPU v4 | 32.0 GB | 1200.0 GB/s | bf16 | 16.94 GB | ~49.6 | ~198.4 q4 |
| NVIDIA GeForce RTX 4090 | 24.0 GB | 1008.0 GB/s | bf16 | 16.94 GB | ~41.7 | ~166.7 q4 |
| AMD Radeon RX 7900 XTX | 24.0 GB | 960.0 GB/s | bf16 | 16.94 GB | ~39.7 | ~158.7 q4 |
| NVIDIA GeForce RTX 5080 | 16.0 GB | 960.0 GB/s | fp8 | 8.47 GB | ~79.4 | ~158.7 q4 |
| NVIDIA GeForce RTX 3090 | 24.0 GB | 936.0 GB/s | bf16 | 16.94 GB | ~38.7 | ~154.7 q4 |
| NVIDIA L40S | 48.0 GB | 864.0 GB/s | bf16 | 16.94 GB | ~35.7 | ~142.8 q4 |
| Apple M3 Ultra | 512.0 GB | 819.0 GB/s | bf16 | 16.94 GB | ~33.9 | ~135.4 q4 |
| AMD Radeon RX 7900 XT | 20.0 GB | 800.0 GB/s | fp8 | 8.47 GB | ~66.1 | ~132.3 q4 |
| Apple M2 Ultra | 192.0 GB | 800.0 GB/s | bf16 | 16.94 GB | ~33.1 | ~132.3 q4 |
| Google TPU v5e | 16.0 GB | 800.0 GB/s | fp8 | 8.47 GB | ~66.1 | ~132.3 q4 |
| NVIDIA GeForce RTX 4080 SUPER | 16.0 GB | 736.0 GB/s | fp8 | 8.47 GB | ~60.8 | ~121.7 q4 |
| NVIDIA GeForce RTX 4070 Ti SUPER | 16.0 GB | 672.0 GB/s | fp8 | 8.47 GB | ~55.6 | ~111.1 q4 |
| AMD Radeon RX 9070 XT | 16.0 GB | 640.0 GB/s | fp8 | 8.47 GB | ~52.9 | ~105.8 q4 |
| Apple M4 Max | 128.0 GB | 546.0 GB/s | bf16 | 16.94 GB | ~22.6 | ~90.3 q4 |
| Apple M1 Max | 64.0 GB | 400.0 GB/s | bf16 | 16.94 GB | ~16.5 | ~66.1 q4 |
| Apple M2 Max | 96.0 GB | 400.0 GB/s | bf16 | 16.94 GB | ~16.5 | ~66.1 q4 |
| Apple M3 Max | 128.0 GB | 400.0 GB/s | bf16 | 16.94 GB | ~16.5 | ~66.1 q4 |
| NVIDIA GeForce RTX 3060 12GB | 12.0 GB | 360.0 GB/s | fp8 | 8.47 GB | ~29.8 | ~59.5 q4 |
| NVIDIA L4 | 24.0 GB | 300.0 GB/s | bf16 | 16.94 GB | ~12.4 | ~49.6 q4 |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16.0 GB | 288.0 GB/s | fp8 | 8.47 GB | ~23.8 | ~47.6 q4 |
| Apple M4 Pro | 64.0 GB | 273.0 GB/s | bf16 | 16.94 GB | ~11.3 | ~45.1 q4 |
| Apple M4 | 32.0 GB | 120.0 GB/s | bf16 | 16.94 GB | ~5.0 | ~19.8 q4 |
Taken from the card's availability section.
| Platform | Id on that platform |
|---|---|
| Hugging Face | LiquidAI/LFM2.5-8B-A1B |
| Benchmark | Evaluated as | Score | Evidence date | Source kind | |
|---|---|---|---|---|---|
| aa_lcr | LFM2.5-8B-A1B | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| critpt | LFM2.5-8B-A1B | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| gpqa_diamond | LFM2.5-8B-A1B | 51.31% | 2026-09-10 evaluated | independent evaluator | source |
This card reports no benchmark scores yet.
| Benchmark | Catalogue standing | Score |
|---|