Can LFM2.5 VL 450M run on the Mac M1 Max 64GB?
Yes. At 8K context the best fit is F16, using about 1.9 GB of the 48.0 GB usable on the Mac M1 Max 64GB. Estimated speed ceiling: ~281 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 0.7 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 2377 |
| 3-bit (Q3_K_M) | 0.8 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 1824 |
| 4-bit (Q4_K_M) • | 0.8 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 1744 |
| 5-bit (Q5_K_M) • | 0.8 GB Fits | 0.9 GB Fits | 1.1 GB Fits | 1536 |
| 6-bit (Q6_K) • | 0.8 GB Fits | 0.9 GB Fits | 1.2 GB Fits | 1363 |
| 8-bit (Q8_0) • | 0.9 GB Fits | 1.0 GB Fits | 1.3 GB Fits | 1055 |
| 16-bit (F16/BF16) • | 1.9 GB Fits | 1.9 GB Fits | 2.2 GB Fits | 281 |
• real GGUF file size from LiquidAI/LFM2.5-VL-450M-GGUF. Speed is a bandwidth ceiling (400 GB/s), not a benchmark. Methodology.
More
LFM2.5 VL 450M on every GPU and Mac · Every model that runs on the Mac M1 Max 64GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (LiquidAI/LFM2.5-VL-450M), Apple specs. Data as of 2026-11-17.