Can I run Holo4 35B-A3B locally?
The official Q4_K_M weights are 21.3GB, plus a separate 0.9GB vision projector, context and runtime memory. The model has 35B total parameters: 3B active does not mean a 3B download. A 32GB Mac is a more realistic starting point than a 24GB Mac, not a tested compatibility guarantee.
How to run Holo4 locally
The publisher provides Q4_K_M GGUF weights and mmproj.f16.gguf under Apache 2.0. Use a current multimodal llama.cpp runtime and load both files. The 21.3GB weights alone leave very little headroom on a 24GB machine; images, context, the projector and other applications add memory use.
Holo4 is a computer-use model, not a turnkey desktop agent. A separate harness must send screenshots, execute requested actions and return tool results. The publisher links hai-agents, but its current SDK quickstart uses a hosted API; that is not evidence of a fully local setup. AICanRun has not tested a local end-to-end harness or phone app, and tokens/s estimates do not measure task completion time.
Official GGUF weights and projector ↗ · Publisher model card ↗
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 |
|---|---|---|---|
| Q4_K_M ★ | 21.3 GB | ~25.4 GB | 0 memory-fit |
Holo4 35B-A3B at Q4_K_M on 151 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 |
|---|---|---|---|---|
| OnePlus 13 | Snapdragon 8 Elite · 24 GB | 25.4 / 20 GB | — | ✕ Won't fit |
| OnePlus 12 | Snapdragon 8 Gen 3 · 24 GB | 25.4 / 20 GB | — | ✕ Won't fit |
| ROG Phone 9 Pro | Snapdragon 8 Elite · 24 GB | 25.4 / 20 GB | — | ✕ Won't fit |
| Huawei Mate X7 | Kirin 9030 Pro · 20 GB | 25.4 / 16 GB | — | ✕ Won't fit |
| Galaxy S25 Ultra | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Galaxy S25 | Snapdragon 8 Elite · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy S24 Ultra | Snapdragon 8 Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy S24 | Samsung Exynos 2400 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy S23 Ultra | Snapdragon 8 Gen 2 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy A55 | Exynos 1480 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| iPhone 16 Pro Max | Apple A18 Pro · 8 GB | 25.4 / 5.2 GB | — | ✕ Won't fit |
| iPhone 16 Pro | Apple A18 Pro · 8 GB | 25.4 / 5.2 GB | — | ✕ Won't fit |
| iPhone 16 | Apple A18 · 8 GB | 25.4 / 5.2 GB | — | ✕ Won't fit |
| iPhone 15 Pro | Apple A17 Pro · 8 GB | 25.4 / 5.2 GB | — | ✕ Won't fit |
| iPhone 15 | Apple A16 Bionic · 6 GB | 25.4 / 3.9 GB | — | ✕ Won't fit |
| iPhone 14 | Apple A15 Bionic · 6 GB | 25.4 / 3.9 GB | — | ✕ Won't fit |
| Pixel 9 Pro | Google Tensor G4 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel 9 | Google Tensor G4 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Pixel 8 Pro | Google Tensor G3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Pixel 8a | Google Tensor G3 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Xiaomi 15 Pro | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xiaomi 14 | Snapdragon 8 Gen 3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Redmi Note 13 Pro | Snapdragon 7s Gen 2 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| POCO X6 Pro | Dimensity 8300 Ultra · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| OPPO Find X8 Pro | Dimensity 9400 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X200 Pro | Dimensity 9400 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X100 Pro | Dimensity 9300 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Nothing Phone (3) | Snapdragon 8s Gen 4 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Nothing Phone (2a) | Dimensity 7200 Pro · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Motorola Edge 50 Ultra | Snapdragon 8s Gen 3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| HONOR Magic7 Pro | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| iPhone 17 | Apple A19 · 8 GB | 25.4 / 5.2 GB | — | ✕ Won't fit |
| iPhone Air | Apple A19 Pro · 12 GB | 25.4 / 7.8 GB | — | ✕ Won't fit |
| iPhone 17 Pro | Apple A19 Pro · 12 GB | 25.4 / 7.8 GB | — | ✕ Won't fit |
| iPhone 17 Pro Max | Apple A19 Pro · 12 GB | 25.4 / 7.8 GB | — | ✕ Won't fit |
| Galaxy S26 | Snapdragon 8 Elite Gen 5 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy S26+ | Snapdragon 8 Elite Gen 5 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy S26 Ultra | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Galaxy S26 FE | Exynos 2500 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Xiaomi 17 | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xiaomi 17 Pro | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xiaomi 18 Pro | Snapdragon 8 Elite Gen 6 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xiaomi 18 Pro Max | Snapdragon 8 Elite Extreme Gen 6 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xiaomi 18 Fold | Xiaomi XRING O3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| nubia NaviX Ultra | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| OnePlus 15 | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X300 Pro | Dimensity 9500 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X500 Pro | Dimensity 9600 Pro · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| vivo X500 Pro Max | Dimensity 9600 Pro · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X300 E | Snapdragon 8 Gen 5 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| OPPO Find X9 Pro | Dimensity 9500 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel 10 | Google Tensor G5 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Pixel 10 Pro | Google Tensor G5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel 11 | Google Tensor G6 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Pixel 11 Pro | Google Tensor G6 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel 11 Pro XL | Google Tensor G6 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| iPhone 16e | Apple A18 · 8 GB | 25.4 / 5.2 GB | — | ✕ Won't fit |
| Pixel 9a | Google Tensor G4 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Galaxy S25 FE | Samsung Exynos 2400 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Nothing Phone (3a) | Snapdragon 7s Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy A16 5G | Exynos 1330 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Galaxy A17 5G | Exynos 1330 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Galaxy A26 5G | Exynos 1380 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Galaxy A36 5G | Snapdragon 6 Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy A56 5G | Exynos 1580 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy Z Fold6 | Snapdragon 8 Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy Z Flip6 | Snapdragon 8 Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy Z Fold7 | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Galaxy Z Flip7 | Exynos 2500 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Moto G (2025) | Dimensity 6300 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Moto G Power (2025) | Dimensity 6300 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Moto G Stylus (2025) | Snapdragon 6 Gen 3 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Moto G (2026) | Dimensity 6300 · 4 GB | 25.4 / 2 GB | — | ✕ Won't fit |
| Moto G Power (2026) | Dimensity 6300 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Moto G Stylus (2026) | Snapdragon 6 Gen 3 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Motorola Razr (2025) | Dimensity 7400X · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Motorola Razr Ultra (2025) | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| OnePlus 13R | Snapdragon 8 Gen 3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| OnePlus 15R | Snapdragon 8 Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel 9 Pro XL | Google Tensor G4 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel 10 Pro XL | Google Tensor G5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| iPhone 17e | Apple A19 · 8 GB | 25.4 / 5.2 GB | — | ✕ Won't fit |
| Pixel 10a | Google Tensor G4 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Galaxy A57 5G | Exynos 1680 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy A37 5G | Exynos 1480 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Motorola Razr (2026) | Dimensity 7450X · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Motorola Razr+ (2026) | Snapdragon 8s Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Motorola Razr Ultra (2026) | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Motorola Edge (2026) | Dimensity 7450 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Nothing Phone (4a) Pro | Snapdragon 7 Gen 4 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| RedMagic 11 Air | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| RedMagic 11S Pro | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Redmi Note 14 Pro 5G | Dimensity 7300 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Redmi Note 15 Pro 5G | Dimensity 7400 Ultra · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Redmi Note 15 5G | Snapdragon 6 Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Redmi Note 14 Pro+ 5G | Snapdragon 7s Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Redmi Note 15 Pro+ 5G | Snapdragon 7s Gen 4 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Xiaomi 15T | Dimensity 8400 Ultra · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Xiaomi 15T Pro | Dimensity 9400+ · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| POCO X7 Pro | Dimensity 8400 Ultra · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Xiaomi MIX Fold 2 | Snapdragon 8+ Gen 1 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Honor 400 | Snapdragon 7 Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Honor Magic8 Pro | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Honor Magic9 | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Honor Magic9 Super Edition | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| CMF Phone 2 Pro | Dimensity 7300 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| AQUOS sense10 | Snapdragon 7s Gen 3 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| AQUOS sense9 | Snapdragon 7s Gen 2 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| AQUOS R10 | Snapdragon 7+ Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Xperia 10 VII | Snapdragon 6 Gen 3 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Xperia 1 VII | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xperia 1 VIII | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Galaxy Z Fold8 | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Galaxy Z Fold8 Ultra | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Galaxy Z Flip8 | Samsung Exynos 2600 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy Z Fold5 | Snapdragon 8 Gen 2 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Galaxy Z Flip5 | Snapdragon 8 Gen 2 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| Xiaomi MIX Fold 3 | Snapdragon 8 Gen 2 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xiaomi MIX Fold 4 | Snapdragon 8 Gen 3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xiaomi MIX Flip | Snapdragon 8 Gen 3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Xiaomi MIX Flip 2 | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Honor Magic V2 | Snapdragon 8 Gen 2 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Honor Magic V3 | Snapdragon 8 Gen 3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Honor Magic V5 | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Honor Magic V6 | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| HONOR Robot Phone | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| OPPO Find N3 | Snapdragon 8 Gen 2 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| OnePlus Open | Snapdragon 8 Gen 2 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| OPPO Find N5 | Snapdragon 8 Elite · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| OPPO Find N6 | Snapdragon 8 Elite Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X Fold3 | Snapdragon 8 Gen 2 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X Fold3 Pro | Snapdragon 8 Gen 3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X Fold5 | Snapdragon 8 Gen 3 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| vivo X Fold6 | Dimensity 9500 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel Fold | Tensor G2 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Pixel 9 Pro Fold | Google Tensor G4 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel 10 Pro Fold | Google Tensor G5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Pixel 11 Pro Fold | Google Tensor G6 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Huawei Mate X6 | Kirin 9020 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Motorola Razr+ (2023) | Snapdragon 8+ Gen 1 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Motorola Razr (2024) | Dimensity 7300X · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Motorola Razr+ (2024) | Snapdragon 8s Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Motorola Razr+ (2025) | Snapdragon 8s Gen 3 · 12 GB | 25.4 / 9 GB | — | ✕ Won't fit |
| Motorola Razr Fold | Snapdragon 8 Gen 5 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| Redmi Note 17 | Snapdragon 4 Gen 4 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| vivo S2 | Dimensity 7360-Turbo · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| vivo V80 Lite 5G (Pakistan) | Dimensity 7360-Turbo · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| iQOO 16 | Snapdragon 8 Elite Extreme Gen 6 · 16 GB | 25.4 / 12 GB | — | ✕ Won't fit |
| iQOO Z11 Lite | Dimensity 6300 · 8 GB | 25.4 / 6 GB | — | ✕ Won't fit |
| vivo Y600i | Snapdragon 4 Gen 2 · 6 GB | 25.4 / 4 GB | — | ✕ Won't fit |
| REDMI 17C 5G | Dimensity 6300 · 4 GB | 25.4 / 2 GB | — | ✕ Won't fit |
~ = bandwidth-based estimate · ✓ = measured on real hardware
Holo4 35B-A3B 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 | 25.6 GB | ~328.6–460.1 tokens/s | ✓ Runs great |
| Mac Studio M3 Ultra | 512 GB | Q4_K_M | 504 GB | 25.6 GB | ~224.3–314 tokens/s | ✓ Runs great |
| Mac Studio M5 Ultra | 256 GB | Q4_K_M | 248 GB | 25.6 GB | ~328.6–460.1 tokens/s | ✓ Runs great |
| Mac Studio M3 Ultra | 256 GB | Q4_K_M | 248 GB | 25.6 GB | ~224.3–314 tokens/s | ✓ Runs great |
| Mac Studio M5 Max | 128 GB | Q4_K_M | 120 GB | 25.6 GB | ~168.2–235.4 tokens/s | ✓ Runs great |
| MacBook Pro M5 Max | 128 GB | Q4_K_M | 120 GB | 25.6 GB | ~168.2–235.4 tokens/s | ✓ Runs great |
| Mac Studio M4 Max | 128 GB | Q4_K_M | 120 GB | 25.6 GB | ~149.5–209.3 tokens/s | ✓ Runs great |
| MacBook Pro M4 Max | 128 GB | Q4_K_M | 120 GB | 25.6 GB | ~149.5–209.3 tokens/s | ✓ Runs great |
| MacBook Pro M3 Max | 128 GB | Q4_K_M | 120 GB | 25.6 GB | ~109.5–153.4 tokens/s | ✓ Runs great |
| Mac Studio M5 Ultra | 96 GB | Q4_K_M | 88 GB | 25.6 GB | ~328.6–460.1 tokens/s | ✓ Runs great |
| Mac Studio M3 Ultra | 96 GB | Q4_K_M | 88 GB | 25.6 GB | ~224.3–314 tokens/s | ✓ Runs great |
| Mac mini M5 Pro | 64 GB | Q4_K_M | 57.6 GB | 25.6 GB | ~84.1–117.7 tokens/s | ✓ Runs great |
| Mac Studio M5 Max | 64 GB | Q4_K_M | 57.6 GB | 25.6 GB | ~168.2–235.4 tokens/s | ✓ Runs great |
| MacBook Pro M5 Pro | 64 GB | Q4_K_M | 57.6 GB | 25.6 GB | ~84.1–117.7 tokens/s | ✓ Runs great |
| MacBook Pro M5 Max | 64 GB | Q4_K_M | 57.6 GB | 25.6 GB | ~168.2–235.4 tokens/s | ✓ Runs great |
| Mac Studio M4 Max | 64 GB | Q4_K_M | 57.6 GB | 25.6 GB | ~149.5–209.3 tokens/s | ✓ Runs great |
| Mac mini M4 Pro | 64 GB | Q4_K_M | 57.6 GB | 25.6 GB | ~74.8–104.7 tokens/s | ✓ Runs great |
| MacBook Pro M4 Max | 64 GB | Q4_K_M | 57.6 GB | 25.6 GB | ~149.5–209.3 tokens/s | ✓ Runs great |
| MacBook Pro M3 Max | 64 GB | Q4_K_M | 57.6 GB | 25.6 GB | ~109.5–153.4 tokens/s | ✓ Runs great |
| Mac mini M5 Pro | 48 GB | Q4_K_M | 43.2 GB | 25.6 GB | ~84.1–117.7 tokens/s | ✓ Runs great |
| Mac Studio M5 Max | 48 GB | Q4_K_M | 43.2 GB | 25.6 GB | ~168.2–235.4 tokens/s | ✓ Runs great |
| MacBook Pro M5 Pro | 48 GB | Q4_K_M | 43.2 GB | 25.6 GB | ~84.1–117.7 tokens/s | ✓ Runs great |
| Mac Studio M4 Max | 48 GB | Q4_K_M | 43.2 GB | 25.6 GB | ~149.5–209.3 tokens/s | ✓ Runs great |
| Mac mini M4 Pro | 48 GB | Q4_K_M | 43.2 GB | 25.6 GB | ~74.8–104.7 tokens/s | ✓ Runs great |
| MacBook Pro M4 Pro | 48 GB | Q4_K_M | 43.2 GB | 25.6 GB | ~74.8–104.7 tokens/s | ✓ Runs great |
| Mac Studio M5 Max | 36 GB | Q4_K_M | 32.4 GB | 25.6 GB | ~126–176.4 tokens/s | ✓ Runs great |
| MacBook Pro M5 Max | 36 GB | Q4_K_M | 32.4 GB | 25.6 GB | ~126–176.4 tokens/s | ✓ Runs great |
| Mac Studio M4 Max | 36 GB | Q4_K_M | 32.4 GB | 25.6 GB | ~112.3–157.2 tokens/s | ✓ Runs great |
| MacBook Pro M4 Max | 36 GB | Q4_K_M | 32.4 GB | 25.6 GB | ~112.3–157.2 tokens/s | ✓ Runs great |
| MacBook Pro M3 Pro | 36 GB | Q4_K_M | 32.4 GB | 25.6 GB | ~41.1–57.5 tokens/s | ✓ Runs great |
| MacBook Pro M3 Max | 36 GB | Q4_K_M | 32.4 GB | 25.6 GB | ~82.2–115 tokens/s | ✓ Runs great |
| Mac mini M6 | 32 GB | Q4_K_M | 28.8 GB | 25.6 GB | ~46.6–65.2 tokens/s | ✓ Runs great |
| Mac mini M5 Pro | 32 GB | Q4_K_M | 28.8 GB | 25.6 GB | ~84.1–117.7 tokens/s | ✓ Runs great |
| MacBook Air M5 | 32 GB | Q4_K_M | 28.8 GB | 25.6 GB | ~35.2–48.6 tokens/s | ✓ Runs great |
| MacBook Air M4 | 32 GB | Q4_K_M | 28.8 GB | 25.6 GB | ~27.6–38.1 tokens/s | ✓ Runs great |
| Mac mini M4 | 32 GB | Q4_K_M | 28.8 GB | 25.6 GB | ~32.9–46 tokens/s | ✓ Runs great |
| Mac mini M6 | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| Mac mini M5 Pro | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Air M5 | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Pro M5 Pro | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Air M4 | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| Mac mini M4 | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| Mac mini M4 Pro | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Air M3 | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Pro M4 Pro | 24 GB | Q4_K_M | 21 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Pro M3 Pro | 18 GB | Q4_K_M | 15 GB | 25.6 GB | — | ✕ Won't fit |
| Mac mini M6 | 16 GB | Q4_K_M | 13 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Air M5 | 16 GB | Q4_K_M | 13 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Air M4 | 16 GB | Q4_K_M | 13 GB | 25.6 GB | — | ✕ Won't fit |
| Mac mini M4 | 16 GB | Q4_K_M | 13 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Air M3 | 16 GB | Q4_K_M | 13 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Air M1 | 16 GB | Q4_K_M | 13 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Neo A18 Pro | 8 GB | Q4_K_M | 5 GB | 25.6 GB | — | ✕ Won't fit |
| MacBook Air M1 | 8 GB | Q4_K_M | 5 GB | 25.6 GB | — | ✕ Won't fit |
FAQ
How much RAM do I need to run Holo4 35B-A3B on a phone?
At Q4_K_M, Holo4 35B-A3B needs ~25.4GB of usable memory (weights + KV cache + runtime). In practice that means no current Android phone or no current iPhone — iOS lets a single app use less of its RAM than Android does.
How fast does Holo4 35B-A3B run on a flagship phone?
It doesn't fit on any of the 151 phones we track at Q4_K_M — it needs ~25.4GB of usable memory.
Can an iPhone run Holo4 35B-A3B?
Not really: the best iPhone we track (iPhone 16 Pro Max) has ~5.2GB usable, but Holo4 35B-A3B needs 25.4GB at Q4_K_M.
What is the best quantization of Holo4 35B-A3B for mobile?
Q4_K_M (21.3GB download) is the size/quality sweet spot. Total memory needed is ~25.4GB once the KV cache and runtime are counted — the download size alone understates it.
How many phones can run Holo4 35B-A3B?
0 of the 151 phones we track have enough estimated usable memory at Q4_K_M; 0 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 Holo4 35B-A3B?
36 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 Holo4 35B-A3B good for on a phone?
It's tagged for vision, coding, reasoning. At 35B parameters (3B active — it's a MoE, so it decodes faster than its size suggests), it prioritizes answer quality over speed — expect slower decoding.