Can medgemma 1.5 4b it run on the Mac M2 24GB?
Yes. At 8K context the best fit is F16, using about 8.4 GB of the 16.1 GB usable on the Mac M2 24GB. Estimated speed ceiling: ~13 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 2.7 GB Fits | 2.8 GB Fits | 3.2 GB Fits | 5.1 GB Fits | 58 |
| 3-bit (Q3_K_M) • | 3.0 GB Fits | 3.1 GB Fits | 3.6 GB Fits | 5.5 GB Fits | 48 |
| 4-bit (Q4_K_M) • | 3.4 GB Fits | 3.5 GB Fits | 4.0 GB Fits | 5.8 GB Fits | 40 |
| 5-bit (Q5_K_M) • | 3.7 GB Fits | 3.8 GB Fits | 4.3 GB Fits | 6.1 GB Fits | 35 |
| 6-bit (Q6_K) • | 4.1 GB Fits | 4.1 GB Fits | 4.6 GB Fits | 6.5 GB Fits | 31 |
| 8-bit (Q8_0) • | 4.9 GB Fits | 5.0 GB Fits | 5.5 GB Fits | 7.4 GB Fits | 24 |
| 16-bit (F16/BF16) • | 8.3 GB Fits | 8.4 GB Fits | 8.9 GB Fits | 10.7 GB Fits | 13 |
• real GGUF file size from unsloth/medgemma-1.5-4b-it-GGUF. Speed is a bandwidth ceiling (100 GB/s), not a benchmark. Methodology.
More
medgemma 1.5 4b it 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 (google/medgemma-1.5-4b-it), Apple specs. Data as of 2026-11-17.