Can LFM2.5 8B A1B run on the RTX 3080 10GB?
Yes. At 8K context the best fit is Q6_K, using about 7.2 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~925 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 3.6 GB Fits | 3.7 GB Fits | 4.0 GB Fits | 2027 |
| 3-bit (Q3_K_M) | 4.5 GB Fits | 4.6 GB Fits | 4.9 GB Fits | 1555 |
| 4-bit (Q4_K_M) • | 5.5 GB Fits | 5.5 GB Fits | 5.8 GB Fits | 1248 |
| 5-bit (Q5_K_M) • | 6.3 GB Fits | 6.4 GB Fits | 6.6 GB Fits | 1067 |
| 6-bit (Q6_K) • | 7.2 GB Fits | 7.2 GB Fits | 7.5 GB Fits | 925 |
| 8-bit (Q8_0) • | 9.1 GB Tight | 9.1 GB Tight | 9.4 GB Tight | 714 |
| 16-bit (F16/BF16) • | 32.3 GB No | 32.3 GB No | 32.6 GB No | — |
• real GGUF file size from LiquidAI/LFM2.5-8B-A1B-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.
More
LFM2.5 8B A1B on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (LiquidAI/LFM2.5-8B-A1B), NVIDIA specs. Data as of 2026-11-17.