Granite 4.2 8B
At the default Q4_K_M, 105 of 139 phones have enough estimated usable memory; 89 also reach 3+ tokens/s. On Mac, 54 of 54 exact configurations pass using that quant or a smaller tracked fallback.
Downloads & memory by quant
The download is only the weights — add KV cache and runtime to get what your phone actually needs. “Memory-fit” only means it can load; “usable” also requires an estimated 3+ tokens/s. Each row uses that row's quant. ★ = recommended.
| Quant | Download | Memory needed | Phone reality |
|---|---|---|---|
| Q2_K | 3.4 GB | ~4.7 GB | 136 memory-fit · 125 usable |
| Q3_K_M | 4.3 GB | ~5.7 GB | 129 memory-fit · 97 usable |
| Q4_0 | 5.1 GB | ~6.5 GB | 105 memory-fit · 91 usable |
| Q4_K_S | 5.1 GB | ~6.5 GB | 105 memory-fit · 91 usable |
| Q4_K_M ★ | 5.3 GB | ~6.7 GB | 105 memory-fit · 89 usable |
| Q5_K_M | 6.3 GB | ~7.8 GB | 105 memory-fit · 89 usable |
| Q6_K | 7.2 GB | ~8.7 GB | 102 memory-fit · 86 usable |
| Q8_0 | 9.3 GB | ~10.9 GB | 59 memory-fit · 59 usable |
Granite 4.2 8B at Q4_K_M on 139 phones
This table is fixed to the recommended Q4_K_M, on each phone's largest RAM option. Counts for smaller quants above will differ. All phones are shown, sorted by fit and estimated experience; tap one for the full report.
| Phone | Chip · RAM | Needs | Speed | Verdict |
|---|---|---|---|---|
| OPPO Find X8 Pro | Dimensity 9400 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| vivo X200 Pro | Dimensity 9400 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Galaxy S26 | Snapdragon 8 Elite Gen 5 · 12 GB | 6.7 / 9 GB | ~7.2 tokens/s | ! Runs, barely |
| Galaxy S26+ | Snapdragon 8 Elite Gen 5 · 12 GB | 6.7 / 9 GB | ~7.2 tokens/s | ! Runs, barely |
| Galaxy S26 Ultra | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Xiaomi 17 | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Xiaomi 17 Pro | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| OnePlus 15 | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| vivo X300 Pro | Dimensity 9500 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| OPPO Find X9 Pro | Dimensity 9500 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| RedMagic 11S Pro | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Xiaomi 15T Pro | Dimensity 9400+ · 12 GB | 6.7 / 9 GB | ~7.2 tokens/s | ! Runs, barely |
| Honor Magic8 Pro | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Xperia 1 VIII | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Galaxy Z Fold8 | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Galaxy Z Fold8 Ultra | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Galaxy Z Flip8 | Samsung Exynos 2600 · 12 GB | 6.7 / 9 GB | ~7.2 tokens/s | ! Runs, barely |
| Honor Magic V6 | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| HONOR Robot Phone | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| OPPO Find N6 | Snapdragon 8 Elite Gen 5 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| vivo X Fold6 | Dimensity 9500 · 16 GB | 6.7 / 12 GB | ~7.2 tokens/s | ! Runs, barely |
| Galaxy S25 Ultra | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Galaxy S25 | Snapdragon 8 Elite · 12 GB | 6.7 / 9 GB | ~6.5 tokens/s | ! Runs, barely |
| Galaxy S24 Ultra | Snapdragon 8 Gen 3 · 12 GB | 6.7 / 9 GB | ~6.5 tokens/s | ! Runs, barely |
| OnePlus 13 | Snapdragon 8 Elite · 24 GB | 6.7 / 20 GB | ~6.5 tokens/s | ! Runs, barely |
| OnePlus 12 | Snapdragon 8 Gen 3 · 24 GB | 6.7 / 20 GB | ~6.5 tokens/s | ! Runs, barely |
| Xiaomi 15 Pro | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Xiaomi 14 | Snapdragon 8 Gen 3 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| vivo X100 Pro | Dimensity 9300 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| ROG Phone 9 Pro | Snapdragon 8 Elite · 24 GB | 6.7 / 20 GB | ~6.5 tokens/s | ! Runs, barely |
| Nothing Phone (3) | Snapdragon 8s Gen 4 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| HONOR Magic7 Pro | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| vivo X300 E | Snapdragon 8 Gen 5 · 12 GB | 6.7 / 9 GB | ~6.5 tokens/s | ! Runs, barely |
| Galaxy Z Fold6 | Snapdragon 8 Gen 3 · 12 GB | 6.7 / 9 GB | ~6.5 tokens/s | ! Runs, barely |
| Galaxy Z Flip6 | Snapdragon 8 Gen 3 · 12 GB | 6.7 / 9 GB | ~6.5 tokens/s | ! Runs, barely |
| Galaxy Z Fold7 | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Galaxy Z Flip7 | Exynos 2500 · 12 GB | 6.7 / 9 GB | ~6.5 tokens/s | ! Runs, barely |
| Motorola Razr Ultra (2025) | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| OnePlus 13R | Snapdragon 8 Gen 3 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| OnePlus 15R | Snapdragon 8 Gen 5 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Motorola Razr Ultra (2026) | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| RedMagic 11 Air | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Xperia 1 VII | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Xiaomi MIX Fold 4 | Snapdragon 8 Gen 3 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Xiaomi MIX Flip | Snapdragon 8 Gen 3 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Xiaomi MIX Flip 2 | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Honor Magic V3 | Snapdragon 8 Gen 3 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Honor Magic V5 | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| OPPO Find N5 | Snapdragon 8 Elite · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| vivo X Fold3 Pro | Snapdragon 8 Gen 3 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| vivo X Fold5 | Snapdragon 8 Gen 3 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Huawei Mate X7 | Kirin 9030 Pro · 20 GB | 6.7 / 16 GB | ~6.5 tokens/s | ! Runs, barely |
| Motorola Razr Fold | Snapdragon 8 Gen 5 · 16 GB | 6.7 / 12 GB | ~6.5 tokens/s | ! Runs, barely |
| Galaxy S24 | Samsung Exynos 2400 · 12 GB | 6.7 / 9 GB | ~5.7 tokens/s | ! Runs, barely |
| Galaxy S23 Ultra | Snapdragon 8 Gen 2 · 12 GB | 6.7 / 9 GB | ~5.7 tokens/s | ! Runs, barely |
| Pixel 9 Pro | Google Tensor G4 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 9 | Google Tensor G4 · 12 GB | 6.7 / 9 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 8 Pro | Google Tensor G3 · 12 GB | 6.7 / 9 GB | ~5.8 tokens/s | ! Runs, barely |
| POCO X6 Pro | Dimensity 8300 Ultra · 12 GB | 6.7 / 9 GB | ~5.8 tokens/s | ! Runs, barely |
| Motorola Edge 50 Ultra | Snapdragon 8s Gen 3 · 16 GB | 6.7 / 12 GB | ~5.7 tokens/s | ! Runs, barely |
| Pixel 10 | Google Tensor G5 · 12 GB | 6.7 / 9 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 10 Pro | Google Tensor G5 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 11 | Google Tensor G6 · 12 GB | 6.7 / 9 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 11 Pro | Google Tensor G6 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 11 Pro XL | Google Tensor G6 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 9 Pro XL | Google Tensor G4 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 10 Pro XL | Google Tensor G5 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Motorola Razr+ (2026) | Snapdragon 8s Gen 3 · 12 GB | 6.7 / 9 GB | ~5.7 tokens/s | ! Runs, barely |
| Xiaomi 15T | Dimensity 8400 Ultra · 12 GB | 6.7 / 9 GB | ~5.8 tokens/s | ! Runs, barely |
| POCO X7 Pro | Dimensity 8400 Ultra · 12 GB | 6.7 / 9 GB | ~5.8 tokens/s | ! Runs, barely |
| AQUOS R10 | Snapdragon 7+ Gen 3 · 12 GB | 6.7 / 9 GB | ~5.7 tokens/s | ! Runs, barely |
| Galaxy Z Fold5 | Snapdragon 8 Gen 2 · 12 GB | 6.7 / 9 GB | ~5.7 tokens/s | ! Runs, barely |
| Xiaomi MIX Fold 3 | Snapdragon 8 Gen 2 · 16 GB | 6.7 / 12 GB | ~5.7 tokens/s | ! Runs, barely |
| Honor Magic V2 | Snapdragon 8 Gen 2 · 16 GB | 6.7 / 12 GB | ~5.7 tokens/s | ! Runs, barely |
| OPPO Find N3 | Snapdragon 8 Gen 2 · 16 GB | 6.7 / 12 GB | ~5.7 tokens/s | ! Runs, barely |
| OnePlus Open | Snapdragon 8 Gen 2 · 16 GB | 6.7 / 12 GB | ~5.7 tokens/s | ! Runs, barely |
| vivo X Fold3 | Snapdragon 8 Gen 2 · 16 GB | 6.7 / 12 GB | ~5.7 tokens/s | ! Runs, barely |
| Pixel 9 Pro Fold | Google Tensor G4 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 10 Pro Fold | Google Tensor G5 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Pixel 11 Pro Fold | Google Tensor G6 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Huawei Mate X6 | Kirin 9020 · 16 GB | 6.7 / 12 GB | ~5.8 tokens/s | ! Runs, barely |
| Motorola Razr+ (2024) | Snapdragon 8s Gen 3 · 12 GB | 6.7 / 9 GB | ~5.7 tokens/s | ! Runs, barely |
| Motorola Razr+ (2025) | Snapdragon 8s Gen 3 · 12 GB | 6.7 / 9 GB | ~5.7 tokens/s | ! Runs, barely |
| Xiaomi MIX Fold 2 | Snapdragon 8+ Gen 1 · 12 GB | 6.7 / 9 GB | ~4.3 tokens/s | ! Runs, barely |
| Pixel Fold | Tensor G2 · 12 GB | 6.7 / 9 GB | ~4.3 tokens/s | ! Runs, barely |
| Motorola Razr+ (2023) | Snapdragon 8+ Gen 1 · 12 GB | 6.7 / 9 GB | ~4.3 tokens/s | ! Runs, barely |
| iPhone Air | Apple A19 Pro · 12 GB | 6.7 / 7.8 GB | ~6.5 tokens/s | ! Runs, barely |
| iPhone 17 Pro | Apple A19 Pro · 12 GB | 6.7 / 7.8 GB | ~6.5 tokens/s | ! Runs, barely |
| iPhone 17 Pro Max | Apple A19 Pro · 12 GB | 6.7 / 7.8 GB | ~6.5 tokens/s | ! Runs, barely |
| Galaxy A57 5G | Exynos 1680 · 12 GB | 6.7 / 9 GB | ~2.9 tokens/s | ! Runs, barely |
| Nothing Phone (4a) Pro | Snapdragon 7 Gen 4 · 12 GB | 6.7 / 9 GB | ~2.9 tokens/s | ! Runs, barely |
| Galaxy A55 | Exynos 1480 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Redmi Note 13 Pro | Snapdragon 7s Gen 2 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Nothing Phone (2a) | Dimensity 7200 Pro · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Nothing Phone (3a) | Snapdragon 7s Gen 3 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Galaxy A36 5G | Snapdragon 6 Gen 3 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Galaxy A56 5G | Exynos 1580 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Galaxy A37 5G | Exynos 1480 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Redmi Note 14 Pro 5G | Dimensity 7300 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Redmi Note 15 Pro 5G | Dimensity 7400 Ultra · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Redmi Note 15 5G | Snapdragon 6 Gen 3 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Redmi Note 14 Pro+ 5G | Snapdragon 7s Gen 3 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Redmi Note 15 Pro+ 5G | Snapdragon 7s Gen 4 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Honor 400 | Snapdragon 7 Gen 3 · 12 GB | 6.7 / 9 GB | ~2.2 tokens/s | ! Runs, barely |
| Motorola Razr (2024) | Dimensity 7300X · 12 GB | 6.7 / 9 GB | ~1.5 tokens/s | ! Runs, barely |
| Pixel 8a | Google Tensor G3 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Galaxy S26 FE | Exynos 2500 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Pixel 9a | Google Tensor G4 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Galaxy S25 FE | Samsung Exynos 2400 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Galaxy A16 5G | Exynos 1330 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Galaxy A17 5G | Exynos 1330 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Galaxy A26 5G | Exynos 1380 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Moto G (2025) | Dimensity 6300 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Moto G Power (2025) | Dimensity 6300 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Moto G Stylus (2025) | Snapdragon 6 Gen 3 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Moto G Power (2026) | Dimensity 6300 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Moto G Stylus (2026) | Snapdragon 6 Gen 3 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Motorola Razr (2025) | Dimensity 7400X · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Pixel 10a | Google Tensor G4 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Motorola Razr (2026) | Dimensity 7450X · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Motorola Edge (2026) | Dimensity 7450 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| CMF Phone 2 Pro | Dimensity 7300 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| AQUOS sense10 | Snapdragon 7s Gen 3 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| AQUOS sense9 | Snapdragon 7s Gen 2 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Xperia 10 VII | Snapdragon 6 Gen 3 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Galaxy Z Flip5 | Snapdragon 8 Gen 2 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| Redmi Note 17 | Snapdragon 4 Gen 4 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| vivo S2 | Dimensity 7360-Turbo · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| iQOO Z11 Lite | Dimensity 6300 · 8 GB | 6.7 / 6 GB | — | ✕ Won't fit |
| iPhone 16 Pro Max | Apple A18 Pro · 8 GB | 6.7 / 5.2 GB | — | ✕ Won't fit |
| iPhone 16 Pro | Apple A18 Pro · 8 GB | 6.7 / 5.2 GB | — | ✕ Won't fit |
| iPhone 16 | Apple A18 · 8 GB | 6.7 / 5.2 GB | — | ✕ Won't fit |
| iPhone 15 Pro | Apple A17 Pro · 8 GB | 6.7 / 5.2 GB | — | ✕ Won't fit |
| iPhone 17 | Apple A19 · 8 GB | 6.7 / 5.2 GB | — | ✕ Won't fit |
| iPhone 16e | Apple A18 · 8 GB | 6.7 / 5.2 GB | — | ✕ Won't fit |
| iPhone 17e | Apple A19 · 8 GB | 6.7 / 5.2 GB | — | ✕ Won't fit |
| iPhone 15 | Apple A16 Bionic · 6 GB | 6.7 / 3.9 GB | — | ✕ Won't fit |
| iPhone 14 | Apple A15 Bionic · 6 GB | 6.7 / 3.9 GB | — | ✕ Won't fit |
| Moto G (2026) | Dimensity 6300 · 4 GB | 6.7 / 2 GB | — | ✕ Won't fit |
~ = bandwidth-based estimate · ✓ = measured on real hardware
Granite 4.2 8B on 54 Mac configurations
Each Mac uses the recommended Q4_K_M at 4K context when it fits, or the largest smaller tracked quant that fits. Each row links to the full report with a macOS-specific setup guide.
| Mac | Unified memory | Quant | Working budget | Needs | Estimated speed | Verdict |
|---|---|---|---|---|---|---|
| Mac Studio M5 Ultra | 512 GB | Q4_K_M | 504 GB | 6.9 GB | ~113.2–158.5 tokens/s | ✓ Runs great |
| Mac Studio M3 Ultra | 512 GB | Q4_K_M | 504 GB | 6.9 GB | ~77.3–108.2 tokens/s | ✓ Runs great |
| Mac Studio M5 Ultra | 256 GB | Q4_K_M | 248 GB | 6.9 GB | ~113.2–158.5 tokens/s | ✓ Runs great |
| Mac Studio M3 Ultra | 256 GB | Q4_K_M | 248 GB | 6.9 GB | ~77.3–108.2 tokens/s | ✓ Runs great |
| Mac Studio M5 Max | 128 GB | Q4_K_M | 120 GB | 6.9 GB | ~57.9–81.1 tokens/s | ✓ Runs great |
| MacBook Pro M5 Max | 128 GB | Q4_K_M | 120 GB | 6.9 GB | ~57.9–81.1 tokens/s | ✓ Runs great |
| Mac Studio M4 Max | 128 GB | Q4_K_M | 120 GB | 6.9 GB | ~51.5–72.1 tokens/s | ✓ Runs great |
| MacBook Pro M4 Max | 128 GB | Q4_K_M | 120 GB | 6.9 GB | ~51.5–72.1 tokens/s | ✓ Runs great |
| MacBook Pro M3 Max | 128 GB | Q4_K_M | 120 GB | 6.9 GB | ~37.7–52.8 tokens/s | ✓ Runs great |
| Mac Studio M5 Ultra | 96 GB | Q4_K_M | 88 GB | 6.9 GB | ~113.2–158.5 tokens/s | ✓ Runs great |
| Mac Studio M3 Ultra | 96 GB | Q4_K_M | 88 GB | 6.9 GB | ~77.3–108.2 tokens/s | ✓ Runs great |
| Mac mini M5 Pro | 64 GB | Q4_K_M | 57.6 GB | 6.9 GB | ~29–40.5 tokens/s | ✓ Runs great |
| Mac Studio M5 Max | 64 GB | Q4_K_M | 57.6 GB | 6.9 GB | ~57.9–81.1 tokens/s | ✓ Runs great |
| MacBook Pro M5 Pro | 64 GB | Q4_K_M | 57.6 GB | 6.9 GB | ~29–40.5 tokens/s | ✓ Runs great |
| MacBook Pro M5 Max | 64 GB | Q4_K_M | 57.6 GB | 6.9 GB | ~57.9–81.1 tokens/s | ✓ Runs great |
| Mac Studio M4 Max | 64 GB | Q4_K_M | 57.6 GB | 6.9 GB | ~51.5–72.1 tokens/s | ✓ Runs great |
| Mac mini M4 Pro | 64 GB | Q4_K_M | 57.6 GB | 6.9 GB | ~25.8–36.1 tokens/s | ✓ Runs great |
| MacBook Pro M4 Max | 64 GB | Q4_K_M | 57.6 GB | 6.9 GB | ~51.5–72.1 tokens/s | ✓ Runs great |
| MacBook Pro M3 Max | 64 GB | Q4_K_M | 57.6 GB | 6.9 GB | ~37.7–52.8 tokens/s | ✓ Runs great |
| Mac mini M5 Pro | 48 GB | Q4_K_M | 43.2 GB | 6.9 GB | ~29–40.5 tokens/s | ✓ Runs great |
| Mac Studio M5 Max | 48 GB | Q4_K_M | 43.2 GB | 6.9 GB | ~57.9–81.1 tokens/s | ✓ Runs great |
| MacBook Pro M5 Pro | 48 GB | Q4_K_M | 43.2 GB | 6.9 GB | ~29–40.5 tokens/s | ✓ Runs great |
| Mac Studio M4 Max | 48 GB | Q4_K_M | 43.2 GB | 6.9 GB | ~51.5–72.1 tokens/s | ✓ Runs great |
| Mac mini M4 Pro | 48 GB | Q4_K_M | 43.2 GB | 6.9 GB | ~25.8–36.1 tokens/s | ✓ Runs great |
| MacBook Pro M4 Pro | 48 GB | Q4_K_M | 43.2 GB | 6.9 GB | ~25.8–36.1 tokens/s | ✓ Runs great |
| Mac Studio M5 Max | 36 GB | Q4_K_M | 32.4 GB | 6.9 GB | ~43.4–60.8 tokens/s | ✓ Runs great |
| MacBook Pro M5 Max | 36 GB | Q4_K_M | 32.4 GB | 6.9 GB | ~43.4–60.8 tokens/s | ✓ Runs great |
| Mac Studio M4 Max | 36 GB | Q4_K_M | 32.4 GB | 6.9 GB | ~38.7–54.2 tokens/s | ✓ Runs great |
| MacBook Pro M4 Max | 36 GB | Q4_K_M | 32.4 GB | 6.9 GB | ~38.7–54.2 tokens/s | ✓ Runs great |
| MacBook Pro M3 Pro | 36 GB | Q4_K_M | 32.4 GB | 6.9 GB | ~14.2–19.8 tokens/s | ✓ Runs great |
| MacBook Pro M3 Max | 36 GB | Q4_K_M | 32.4 GB | 6.9 GB | ~28.3–39.6 tokens/s | ✓ Runs great |
| Mac mini M6 | 32 GB | Q4_K_M | 28.8 GB | 6.9 GB | ~16–22.5 tokens/s | ✓ Runs great |
| Mac mini M5 Pro | 32 GB | Q4_K_M | 28.8 GB | 6.9 GB | ~29–40.5 tokens/s | ✓ Runs great |
| MacBook Air M5 | 32 GB | Q4_K_M | 28.8 GB | 6.9 GB | ~12.1–16.7 tokens/s | ✓ Runs great |
| MacBook Air M4 | 32 GB | Q4_K_M | 28.8 GB | 6.9 GB | ~9.5–13.1 tokens/s | ✓ Runs great |
| Mac mini M4 | 32 GB | Q4_K_M | 28.8 GB | 6.9 GB | ~11.3–15.8 tokens/s | ✓ Runs great |
| Mac mini M6 | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~16–22.5 tokens/s | ✓ Runs great |
| Mac mini M5 Pro | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~29–40.5 tokens/s | ✓ Runs great |
| MacBook Air M5 | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~12.1–16.7 tokens/s | ✓ Runs great |
| MacBook Pro M5 Pro | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~29–40.5 tokens/s | ✓ Runs great |
| MacBook Air M4 | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~9.5–13.1 tokens/s | ✓ Runs great |
| Mac mini M4 | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~11.3–15.8 tokens/s | ✓ Runs great |
| Mac mini M4 Pro | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~25.8–36.1 tokens/s | ✓ Runs great |
| MacBook Air M3 | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~7.9–10.9 tokens/s | ✓ Runs great |
| MacBook Pro M4 Pro | 24 GB | Q4_K_M | 21 GB | 6.9 GB | ~25.8–36.1 tokens/s | ✓ Runs great |
| MacBook Pro M3 Pro | 18 GB | Q4_K_M | 15 GB | 6.9 GB | ~14.2–19.8 tokens/s | ✓ Runs great |
| Mac mini M6 | 16 GB | Q4_K_M | 13 GB | 6.9 GB | ~16–22.5 tokens/s | ✓ Runs great |
| MacBook Air M5 | 16 GB | Q4_K_M | 13 GB | 6.9 GB | ~12.1–16.7 tokens/s | ✓ Runs great |
| MacBook Air M4 | 16 GB | Q4_K_M | 13 GB | 6.9 GB | ~9.5–13.1 tokens/s | ✓ Runs great |
| Mac mini M4 | 16 GB | Q4_K_M | 13 GB | 6.9 GB | ~11.3–15.8 tokens/s | ✓ Runs great |
| MacBook Air M3 | 16 GB | Q4_K_M | 13 GB | 6.9 GB | ~7.9–10.9 tokens/s | ✓ Runs great |
| MacBook Air M1 | 16 GB | Q4_K_M | 13 GB | 6.9 GB | ~5.4–7.5 tokens/s | ✓ Runs great |
| MacBook Neo A18 Pro | 8 GB | Q2_Ksmaller version | 5 GB | 4.9 GB | ~7.4–10.2 tokens/s | ! Runs, barely |
| MacBook Air M1 | 8 GB | Q2_Ksmaller version | 5 GB | 4.9 GB | ~8.4–11.7 tokens/s | ! Runs, barely |
FAQ
How much RAM do I need to run Granite 4.2 8B on a phone?
At Q4_K_M, Granite 4.2 8B needs ~6.7GB of usable memory (weights + KV cache + runtime). In practice that means a 12GB+ Android phone or a 12GB+ iPhone — iOS lets a single app use less of its RAM than Android does.
How fast does Granite 4.2 8B run on a flagship phone?
On the OPPO Find X8 Pro (Dimensity 9400) it runs at ~7.2 tokens/s at Q4_K_M, estimated from memory bandwidth. Anything above ~8 tokens/s feels smooth for chat.
Can an iPhone run Granite 4.2 8B?
Yes — the iPhone Air runs it at ~6.5 tokens/s at Q4_K_M, using 6.7GB of its ~7.8GB usable memory.
What is the best quantization of Granite 4.2 8B for mobile?
Q4_K_M (5.3GB download) is the size/quality sweet spot of the 8 quants available. Total memory needed is ~6.7GB once the KV cache and runtime are counted — the download size alone understates it.
How many phones can run Granite 4.2 8B?
105 of the 139 phones we track have enough estimated usable memory at Q4_K_M; 89 also reach our usable-speed threshold of 3 tokens/s, and 0 run smoothly. Memory-fit alone does not mean a good experience.
Which Macs can run Granite 4.2 8B?
54 of the 54 exact Mac configurations we track have enough estimated working memory. Each Mac uses the recommended Q4_K_M when it fits, or the largest smaller tracked quant that fits, and separates installed unified memory, the macOS reserve, and estimated speed.
What is Granite 4.2 8B good for on a phone?
It's tagged for chat, coding, reasoning. At 8B parameters, it balances quality and speed for daily use.