Can LFM2.5 VL 450M run on the Mac M2 24GB?
Yes. At 8K context the best fit is F16, using about 1.9 GB of the 16.1 GB usable on the Mac M2 24GB. Estimated speed ceiling: ~70 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 | 594 |
| 3-bit (Q3_K_M) | 0.8 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 456 |
| 4-bit (Q4_K_M) • | 0.8 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 436 |
| 5-bit (Q5_K_M) • | 0.8 GB Fits | 0.9 GB Fits | 1.1 GB Fits | 384 |
| 6-bit (Q6_K) • | 0.8 GB Fits | 0.9 GB Fits | 1.2 GB Fits | 341 |
| 8-bit (Q8_0) • | 0.9 GB Fits | 1.0 GB Fits | 1.3 GB Fits | 264 |
| 16-bit (F16/BF16) • | 1.9 GB Fits | 1.9 GB Fits | 2.2 GB Fits | 70 |
• real GGUF file size from LiquidAI/LFM2.5-VL-450M-GGUF. Speed is a bandwidth ceiling (100 GB/s), not a benchmark. Methodology.
More
LFM2.5 VL 450M on every GPU and Mac · Every model that runs on the Mac M2 24GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (LiquidAI/LFM2.5-VL-450M), Apple specs. Model data last checked 2026-11-17; refreshed hourly.