aicanrun

Agents-A1 4B

At the default Q4_K_M, 139 of 140 phones have enough estimated usable memory; 127 also reach 3+ tokens/s. On Mac, 54 of 54 exact configurations pass using that quant or a smaller tracked fallback.

Params
4B
Family
agents-a1
Released
2026-07
Tags
chat · coding · vision · reasoning
Weights
Agents-A1-4B-Q4_K_M-GGUF ↗

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.

QuantDownloadMemory neededPhone reality
Q4_K_M ★2.7 GB~3.7 GB139 memory-fit · 127 usable

Agents-A1 4B at Q4_K_M on 140 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.

PhoneChip · RAMNeedsSpeedVerdict
OPPO Find X8 ProDimensity 9400 · 16 GB3.7 / 12 GB~14.2 tokens/s✓ Runs great
vivo X200 ProDimensity 9400 · 16 GB3.7 / 12 GB~14.2 tokens/s✓ Runs great
Galaxy S26Snapdragon 8 Elite Gen 5 · 12 GB3.7 / 9 GB~14.1 tokens/s✓ Runs great
Galaxy S26+Snapdragon 8 Elite Gen 5 · 12 GB3.7 / 9 GB~14.1 tokens/s✓ Runs great
Galaxy S26 UltraSnapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
Xiaomi 17Snapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
Xiaomi 17 ProSnapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
OnePlus 15Snapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
vivo X300 ProDimensity 9500 · 16 GB3.7 / 12 GB~14.2 tokens/s✓ Runs great
OPPO Find X9 ProDimensity 9500 · 16 GB3.7 / 12 GB~14.2 tokens/s✓ Runs great
RedMagic 11S ProSnapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
Xiaomi 15T ProDimensity 9400+ · 12 GB3.7 / 9 GB~14.2 tokens/s✓ Runs great
Honor Magic8 ProSnapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
Xperia 1 VIIISnapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
Galaxy Z Fold8Snapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
Galaxy Z Fold8 UltraSnapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
Galaxy Z Flip8Samsung Exynos 2600 · 12 GB3.7 / 9 GB~14.2 tokens/s✓ Runs great
Honor Magic V6Snapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
HONOR Robot PhoneSnapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
OPPO Find N6Snapdragon 8 Elite Gen 5 · 16 GB3.7 / 12 GB~14.1 tokens/s✓ Runs great
vivo X Fold6Dimensity 9500 · 16 GB3.7 / 12 GB~14.2 tokens/s✓ Runs great
Galaxy S25 UltraSnapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Galaxy S25Snapdragon 8 Elite · 12 GB3.7 / 9 GB~12.8 tokens/s✓ Runs great
Galaxy S24 UltraSnapdragon 8 Gen 3 · 12 GB3.7 / 9 GB~12.8 tokens/s✓ Runs great
OnePlus 13Snapdragon 8 Elite · 24 GB3.7 / 20 GB~12.8 tokens/s✓ Runs great
OnePlus 12Snapdragon 8 Gen 3 · 24 GB3.7 / 20 GB~12.8 tokens/s✓ Runs great
Xiaomi 15 ProSnapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Xiaomi 14Snapdragon 8 Gen 3 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
vivo X100 ProDimensity 9300 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
ROG Phone 9 ProSnapdragon 8 Elite · 24 GB3.7 / 20 GB~12.8 tokens/s✓ Runs great
Nothing Phone (3)Snapdragon 8s Gen 4 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
HONOR Magic7 ProSnapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
iPhone AirApple A19 Pro · 12 GB3.7 / 7.8 GB~12.8 tokens/s✓ Runs great
iPhone 17 ProApple A19 Pro · 12 GB3.7 / 7.8 GB~12.8 tokens/s✓ Runs great
iPhone 17 Pro MaxApple A19 Pro · 12 GB3.7 / 7.8 GB~12.8 tokens/s✓ Runs great
Galaxy S26 FEExynos 2500 · 8 GB3.7 / 6 GB~12.8 tokens/s✓ Runs great
vivo X300 ESnapdragon 8 Gen 5 · 12 GB3.7 / 9 GB~12.8 tokens/s✓ Runs great
Galaxy Z Fold6Snapdragon 8 Gen 3 · 12 GB3.7 / 9 GB~12.8 tokens/s✓ Runs great
Galaxy Z Flip6Snapdragon 8 Gen 3 · 12 GB3.7 / 9 GB~12.8 tokens/s✓ Runs great
Galaxy Z Fold7Snapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Galaxy Z Flip7Exynos 2500 · 12 GB3.7 / 9 GB~12.8 tokens/s✓ Runs great
Motorola Razr Ultra (2025)Snapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
OnePlus 13RSnapdragon 8 Gen 3 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
OnePlus 15RSnapdragon 8 Gen 5 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Motorola Razr Ultra (2026)Snapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
RedMagic 11 AirSnapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Xperia 1 VIISnapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Xiaomi MIX Fold 4Snapdragon 8 Gen 3 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Xiaomi MIX FlipSnapdragon 8 Gen 3 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Xiaomi MIX Flip 2Snapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Honor Magic V3Snapdragon 8 Gen 3 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Honor Magic V5Snapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
OPPO Find N5Snapdragon 8 Elite · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
vivo X Fold3 ProSnapdragon 8 Gen 3 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
vivo X Fold5Snapdragon 8 Gen 3 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Huawei Mate X7Kirin 9030 Pro · 20 GB3.7 / 16 GB~12.8 tokens/s✓ Runs great
Motorola Razr FoldSnapdragon 8 Gen 5 · 16 GB3.7 / 12 GB~12.8 tokens/s✓ Runs great
Galaxy S24Samsung Exynos 2400 · 12 GB3.7 / 9 GB~11.2 tokens/s✓ Runs great
Galaxy S23 UltraSnapdragon 8 Gen 2 · 12 GB3.7 / 9 GB~11.2 tokens/s✓ Runs great
Pixel 9 ProGoogle Tensor G4 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Pixel 9Google Tensor G4 · 12 GB3.7 / 9 GB~11.4 tokens/s✓ Runs great
Pixel 8 ProGoogle Tensor G3 · 12 GB3.7 / 9 GB~11.4 tokens/s✓ Runs great
Pixel 8aGoogle Tensor G3 · 8 GB3.7 / 6 GB~11.4 tokens/s✓ Runs great
POCO X6 ProDimensity 8300 Ultra · 12 GB3.7 / 9 GB~11.4 tokens/s✓ Runs great
Motorola Edge 50 UltraSnapdragon 8s Gen 3 · 16 GB3.7 / 12 GB~11.2 tokens/s✓ Runs great
Pixel 10Google Tensor G5 · 12 GB3.7 / 9 GB~11.4 tokens/s✓ Runs great
Pixel 10 ProGoogle Tensor G5 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Pixel 11Google Tensor G6 · 12 GB3.7 / 9 GB~11.4 tokens/s✓ Runs great
Pixel 11 ProGoogle Tensor G6 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Pixel 11 Pro XLGoogle Tensor G6 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Pixel 9aGoogle Tensor G4 · 8 GB3.7 / 6 GB~11.4 tokens/s✓ Runs great
Galaxy S25 FESamsung Exynos 2400 · 8 GB3.7 / 6 GB~11.2 tokens/s✓ Runs great
Pixel 9 Pro XLGoogle Tensor G4 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Pixel 10 Pro XLGoogle Tensor G5 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Pixel 10aGoogle Tensor G4 · 8 GB3.7 / 6 GB~11.4 tokens/s✓ Runs great
Motorola Razr+ (2026)Snapdragon 8s Gen 3 · 12 GB3.7 / 9 GB~11.2 tokens/s✓ Runs great
Xiaomi 15TDimensity 8400 Ultra · 12 GB3.7 / 9 GB~11.4 tokens/s✓ Runs great
POCO X7 ProDimensity 8400 Ultra · 12 GB3.7 / 9 GB~11.4 tokens/s✓ Runs great
AQUOS R10Snapdragon 7+ Gen 3 · 12 GB3.7 / 9 GB~11.2 tokens/s✓ Runs great
Galaxy Z Fold5Snapdragon 8 Gen 2 · 12 GB3.7 / 9 GB~11.2 tokens/s✓ Runs great
Galaxy Z Flip5Snapdragon 8 Gen 2 · 8 GB3.7 / 6 GB~11.2 tokens/s✓ Runs great
Xiaomi MIX Fold 3Snapdragon 8 Gen 2 · 16 GB3.7 / 12 GB~11.2 tokens/s✓ Runs great
Honor Magic V2Snapdragon 8 Gen 2 · 16 GB3.7 / 12 GB~11.2 tokens/s✓ Runs great
OPPO Find N3Snapdragon 8 Gen 2 · 16 GB3.7 / 12 GB~11.2 tokens/s✓ Runs great
OnePlus OpenSnapdragon 8 Gen 2 · 16 GB3.7 / 12 GB~11.2 tokens/s✓ Runs great
vivo X Fold3Snapdragon 8 Gen 2 · 16 GB3.7 / 12 GB~11.2 tokens/s✓ Runs great
Pixel 9 Pro FoldGoogle Tensor G4 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Pixel 10 Pro FoldGoogle Tensor G5 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Pixel 11 Pro FoldGoogle Tensor G6 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Huawei Mate X6Kirin 9020 · 16 GB3.7 / 12 GB~11.4 tokens/s✓ Runs great
Motorola Razr+ (2024)Snapdragon 8s Gen 3 · 12 GB3.7 / 9 GB~11.2 tokens/s✓ Runs great
Motorola Razr+ (2025)Snapdragon 8s Gen 3 · 12 GB3.7 / 9 GB~11.2 tokens/s✓ Runs great
iPhone 17Apple A19 · 8 GB3.7 / 5.2 GB~11.4 tokens/s✓ Runs great
iPhone 17eApple A19 · 8 GB3.7 / 5.2 GB~11.4 tokens/s✓ Runs great
Xiaomi MIX Fold 2Snapdragon 8+ Gen 1 · 12 GB3.7 / 9 GB~8.5 tokens/s✓ Runs great
Pixel FoldTensor G2 · 12 GB3.7 / 9 GB~8.5 tokens/s✓ Runs great
Motorola Razr+ (2023)Snapdragon 8+ Gen 1 · 12 GB3.7 / 9 GB~8.5 tokens/s✓ Runs great
iPhone 16 Pro MaxApple A18 Pro · 8 GB3.7 / 5.2 GB~10 tokens/s✓ Runs great
iPhone 16 ProApple A18 Pro · 8 GB3.7 / 5.2 GB~10 tokens/s✓ Runs great
iPhone 16Apple A18 · 8 GB3.7 / 5.2 GB~10 tokens/s✓ Runs great
iPhone 16eApple A18 · 8 GB3.7 / 5.2 GB~10 tokens/s✓ Runs great
iPhone 15 ProApple A17 Pro · 8 GB3.7 / 5.2 GB~8.5 tokens/s✓ Runs great
Galaxy A57 5GExynos 1680 · 12 GB3.7 / 9 GB~5.7 tokens/s! Runs, barely
Nothing Phone (4a) ProSnapdragon 7 Gen 4 · 12 GB3.7 / 9 GB~5.6 tokens/s! Runs, barely
Galaxy A55Exynos 1480 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Redmi Note 13 ProSnapdragon 7s Gen 2 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Nothing Phone (2a)Dimensity 7200 Pro · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Nothing Phone (3a)Snapdragon 7s Gen 3 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Galaxy A26 5GExynos 1380 · 8 GB3.7 / 6 GB~4.3 tokens/s! Runs, barely
Galaxy A36 5GSnapdragon 6 Gen 3 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Galaxy A56 5GExynos 1580 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Moto G Stylus (2025)Snapdragon 6 Gen 3 · 8 GB3.7 / 6 GB~4.3 tokens/s! Runs, barely
Moto G Stylus (2026)Snapdragon 6 Gen 3 · 8 GB3.7 / 6 GB~4.3 tokens/s! Runs, barely
Galaxy A37 5GExynos 1480 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Motorola Edge (2026)Dimensity 7450 · 8 GB3.7 / 6 GB~4.3 tokens/s! Runs, barely
Redmi Note 14 Pro 5GDimensity 7300 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Redmi Note 15 Pro 5GDimensity 7400 Ultra · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Redmi Note 15 5GSnapdragon 6 Gen 3 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Redmi Note 14 Pro+ 5GSnapdragon 7s Gen 3 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Redmi Note 15 Pro+ 5GSnapdragon 7s Gen 4 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
Honor 400Snapdragon 7 Gen 3 · 12 GB3.7 / 9 GB~4.3 tokens/s! Runs, barely
CMF Phone 2 ProDimensity 7300 · 8 GB3.7 / 6 GB~4.3 tokens/s! Runs, barely
AQUOS sense10Snapdragon 7s Gen 3 · 8 GB3.7 / 6 GB~4.3 tokens/s! Runs, barely
AQUOS sense9Snapdragon 7s Gen 2 · 8 GB3.7 / 6 GB~4.3 tokens/s! Runs, barely
Xperia 10 VIISnapdragon 6 Gen 3 · 8 GB3.7 / 6 GB~4.3 tokens/s! Runs, barely
Galaxy A16 5GExynos 1330 · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
Galaxy A17 5GExynos 1330 · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
Moto G (2025)Dimensity 6300 · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
Moto G Power (2025)Dimensity 6300 · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
Moto G Power (2026)Dimensity 6300 · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
Motorola Razr (2025)Dimensity 7400X · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
Motorola Razr (2026)Dimensity 7450X · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
Motorola Razr (2024)Dimensity 7300X · 12 GB3.7 / 9 GB~2.9 tokens/s! Runs, barely
Redmi Note 17Snapdragon 4 Gen 4 · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
vivo S2Dimensity 7360-Turbo · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
vivo V80 Lite 5G (Pakistan)Dimensity 7360-Turbo · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
iQOO Z11 LiteDimensity 6300 · 8 GB3.7 / 6 GB~2.9 tokens/s! Runs, barely
iPhone 15Apple A16 Bionic · 6 GB3.7 / 3.9 GB~8.5 tokens/s! Runs, barely
iPhone 14Apple A15 Bionic · 6 GB3.7 / 3.9 GB~5.7 tokens/s! Runs, barely
Moto G (2026)Dimensity 6300 · 4 GB3.7 / 2 GB—✕ Won't fit

~ = bandwidth-based estimate · ✓ = measured on real hardware

Agents-A1 4B 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.

MacUnified memoryQuantWorking budgetNeedsEstimated speedVerdict
Mac Studio M5 Ultra512 GBQ4_K_M504 GB3.9 GB~222.2–311.1 tokens/s✓ Runs great
Mac Studio M3 Ultra512 GBQ4_K_M504 GB3.9 GB~151.7–212.3 tokens/s✓ Runs great
Mac Studio M5 Ultra256 GBQ4_K_M248 GB3.9 GB~222.2–311.1 tokens/s✓ Runs great
Mac Studio M3 Ultra256 GBQ4_K_M248 GB3.9 GB~151.7–212.3 tokens/s✓ Runs great
Mac Studio M5 Max128 GBQ4_K_M120 GB3.9 GB~113.7–159.2 tokens/s✓ Runs great
MacBook Pro M5 Max128 GBQ4_K_M120 GB3.9 GB~113.7–159.2 tokens/s✓ Runs great
Mac Studio M4 Max128 GBQ4_K_M120 GB3.9 GB~101.1–141.6 tokens/s✓ Runs great
MacBook Pro M4 Max128 GBQ4_K_M120 GB3.9 GB~101.1–141.6 tokens/s✓ Runs great
MacBook Pro M3 Max128 GBQ4_K_M120 GB3.9 GB~74.1–103.7 tokens/s✓ Runs great
Mac Studio M5 Ultra96 GBQ4_K_M88 GB3.9 GB~222.2–311.1 tokens/s✓ Runs great
Mac Studio M3 Ultra96 GBQ4_K_M88 GB3.9 GB~151.7–212.3 tokens/s✓ Runs great
Mac mini M5 Pro64 GBQ4_K_M57.6 GB3.9 GB~56.9–79.6 tokens/s✓ Runs great
Mac Studio M5 Max64 GBQ4_K_M57.6 GB3.9 GB~113.7–159.2 tokens/s✓ Runs great
MacBook Pro M5 Pro64 GBQ4_K_M57.6 GB3.9 GB~56.9–79.6 tokens/s✓ Runs great
MacBook Pro M5 Max64 GBQ4_K_M57.6 GB3.9 GB~113.7–159.2 tokens/s✓ Runs great
Mac Studio M4 Max64 GBQ4_K_M57.6 GB3.9 GB~101.1–141.6 tokens/s✓ Runs great
Mac mini M4 Pro64 GBQ4_K_M57.6 GB3.9 GB~50.6–70.8 tokens/s✓ Runs great
MacBook Pro M4 Max64 GBQ4_K_M57.6 GB3.9 GB~101.1–141.6 tokens/s✓ Runs great
MacBook Pro M3 Max64 GBQ4_K_M57.6 GB3.9 GB~74.1–103.7 tokens/s✓ Runs great
Mac mini M5 Pro48 GBQ4_K_M43.2 GB3.9 GB~56.9–79.6 tokens/s✓ Runs great
Mac Studio M5 Max48 GBQ4_K_M43.2 GB3.9 GB~113.7–159.2 tokens/s✓ Runs great
MacBook Pro M5 Pro48 GBQ4_K_M43.2 GB3.9 GB~56.9–79.6 tokens/s✓ Runs great
Mac Studio M4 Max48 GBQ4_K_M43.2 GB3.9 GB~101.1–141.6 tokens/s✓ Runs great
Mac mini M4 Pro48 GBQ4_K_M43.2 GB3.9 GB~50.6–70.8 tokens/s✓ Runs great
MacBook Pro M4 Pro48 GBQ4_K_M43.2 GB3.9 GB~50.6–70.8 tokens/s✓ Runs great
Mac Studio M5 Max36 GBQ4_K_M32.4 GB3.9 GB~85.2–119.3 tokens/s✓ Runs great
MacBook Pro M5 Max36 GBQ4_K_M32.4 GB3.9 GB~85.2–119.3 tokens/s✓ Runs great
Mac Studio M4 Max36 GBQ4_K_M32.4 GB3.9 GB~75.9–106.3 tokens/s✓ Runs great
MacBook Pro M4 Max36 GBQ4_K_M32.4 GB3.9 GB~75.9–106.3 tokens/s✓ Runs great
MacBook Pro M3 Pro36 GBQ4_K_M32.4 GB3.9 GB~27.8–38.9 tokens/s✓ Runs great
MacBook Pro M3 Max36 GBQ4_K_M32.4 GB3.9 GB~55.6–77.8 tokens/s✓ Runs great
Mac mini M632 GBQ4_K_M28.8 GB3.9 GB~31.5–44.1 tokens/s✓ Runs great
Mac mini M5 Pro32 GBQ4_K_M28.8 GB3.9 GB~56.9–79.6 tokens/s✓ Runs great
MacBook Air M532 GBQ4_K_M28.8 GB3.9 GB~23.8–32.9 tokens/s✓ Runs great
MacBook Air M432 GBQ4_K_M28.8 GB3.9 GB~18.7–25.8 tokens/s✓ Runs great
Mac mini M432 GBQ4_K_M28.8 GB3.9 GB~22.2–31.1 tokens/s✓ Runs great
Mac mini M624 GBQ4_K_M21 GB3.9 GB~31.5–44.1 tokens/s✓ Runs great
Mac mini M5 Pro24 GBQ4_K_M21 GB3.9 GB~56.9–79.6 tokens/s✓ Runs great
MacBook Air M524 GBQ4_K_M21 GB3.9 GB~23.8–32.9 tokens/s✓ Runs great
MacBook Pro M5 Pro24 GBQ4_K_M21 GB3.9 GB~56.9–79.6 tokens/s✓ Runs great
MacBook Air M424 GBQ4_K_M21 GB3.9 GB~18.7–25.8 tokens/s✓ Runs great
Mac mini M424 GBQ4_K_M21 GB3.9 GB~22.2–31.1 tokens/s✓ Runs great
Mac mini M4 Pro24 GBQ4_K_M21 GB3.9 GB~50.6–70.8 tokens/s✓ Runs great
MacBook Air M324 GBQ4_K_M21 GB3.9 GB~15.6–21.5 tokens/s✓ Runs great
MacBook Pro M4 Pro24 GBQ4_K_M21 GB3.9 GB~50.6–70.8 tokens/s✓ Runs great
MacBook Pro M3 Pro18 GBQ4_K_M15 GB3.9 GB~27.8–38.9 tokens/s✓ Runs great
Mac mini M616 GBQ4_K_M13 GB3.9 GB~31.5–44.1 tokens/s✓ Runs great
MacBook Air M516 GBQ4_K_M13 GB3.9 GB~23.8–32.9 tokens/s✓ Runs great
MacBook Air M416 GBQ4_K_M13 GB3.9 GB~18.7–25.8 tokens/s✓ Runs great
Mac mini M416 GBQ4_K_M13 GB3.9 GB~22.2–31.1 tokens/s✓ Runs great
MacBook Air M316 GBQ4_K_M13 GB3.9 GB~15.6–21.5 tokens/s✓ Runs great
MacBook Air M116 GBQ4_K_M13 GB3.9 GB~10.6–14.7 tokens/s✓ Runs great
MacBook Neo A18 Pro8 GBQ4_K_M5 GB3.9 GB~9.3–12.9 tokens/s! Runs, barely
MacBook Air M18 GBQ4_K_M5 GB3.9 GB~10.6–14.7 tokens/s! Runs, barely

FAQ

How much RAM do I need to run Agents-A1 4B on a phone?

At Q4_K_M, Agents-A1 4B needs ~3.7GB of usable memory (weights + KV cache + runtime). In practice that means a 6GB+ Android phone or a 6GB+ iPhone — iOS lets a single app use less of its RAM than Android does.

How fast does Agents-A1 4B run on a flagship phone?

On the OPPO Find X8 Pro (Dimensity 9400) it runs at ~14.2 tokens/s at Q4_K_M, estimated from memory bandwidth. Anything above ~8 tokens/s feels smooth for chat.

Can an iPhone run Agents-A1 4B?

Yes — the iPhone Air runs it at ~12.8 tokens/s at Q4_K_M, using 3.7GB of its ~7.8GB usable memory.

What is the best quantization of Agents-A1 4B for mobile?

Q4_K_M (2.7GB download) is the size/quality sweet spot. Total memory needed is ~3.7GB once the KV cache and runtime are counted — the download size alone understates it.

How many phones can run Agents-A1 4B?

139 of the 140 phones we track have enough estimated usable memory at Q4_K_M; 127 also reach our usable-speed threshold of 3 tokens/s, and 102 run smoothly. Memory-fit alone does not mean a good experience.

Which Macs can run Agents-A1 4B?

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 Agents-A1 4B good for on a phone?

It's tagged for chat, coding, vision, reasoning. At 4B parameters, it's a fast, lightweight pick for quick tasks.

Similar models

Qwen3 4BQwen 3.5 4BGemma 4 E4BTernary Bonsai 4BNemotron 3 Nano 4B