aicanrun

AI Models for Galaxy Z Flip8 — What runs on 12GB

34 great · 15 slow · 44 won't fit
Chip
Samsung Exynos 2600
Memory bandwidth
85.3 GB/s
NPU
59 TOPS
RAM options
12 GB
Usable for models
~9 GB
Year
2026

Specs checked against manufacturer and public documentation on . Exynos 2600 in Korea and most international markets; Snapdragon 8 Elite Gen 5 for Galaxy in the US — tracks the Exynos variant.

What runs on the Galaxy Z Flip8

All 93 models at their recommended quant, on the 12GB configuration. Select any row for the full report.

ModelParamsQuantNeedsSpeedVerdict
Qwen3 0.6B0.6BQ8_01.3 GB~64 tokens/s✓ Runs great
Qwen3 1.7B1.7BQ8_02.6 GB~21.3 tokens/s✓ Runs great
Qwen3 4B4BQ4_K_M3.5 GB~15.4 tokens/s✓ Runs great
Llama 3.2 1B1.2BQ4_K_M1.5 GB~48 tokens/s✓ Runs great
Llama 3.2 3B3.2BQ4_K_M2.9 GB~19.2 tokens/s✓ Runs great
Gemma 3 1B1BQ4_K_M1.5 GB~48 tokens/s✓ Runs great
Gemma 3 4B4.3BQ4_K_M3.5 GB~15.4 tokens/s✓ Runs great
Phi-4 Mini 3.8B3.8BQ4_K_M3.5 GB~15.4 tokens/s✓ Runs great
DeepSeek R1 Distill 1.5B1.8BQ4_K_M1.9 GB~34.9 tokens/s✓ Runs great
SmolLM2 1.7B1.7BQ4_K_M1.9 GB~34.9 tokens/s✓ Runs great
SmolLM3 3B3.1BQ4_K_M2.8 GB~20.2 tokens/s✓ Runs great
Qwen 3.5 2B2BQ4_K_M2.1 GB~29.5 tokens/s✓ Runs great
Ternary Bonsai 8B8BQ2_03.5 GB~17.4 tokens/s✓ Runs great
Ternary Bonsai 4B4BQ2_02 GB~34.9 tokens/s✓ Runs great
Ternary Bonsai 1.7B1.7BQ2_01.2 GB~76.8 tokens/s✓ Runs great
Ministral 3 3B3BQ4_K_M3 GB~18.3 tokens/s✓ Runs great
LFM2.5 2.6B2.7BQ4_K_M2.6 GB~22.6 tokens/s✓ Runs great
LFM2.5 8B-A1B8BQ4_K_M6.6 GB~59.1 tokens/s✓ Runs great
LFM2.5-VL 3B3.1BQ4_K_M2.6 GB~22.6 tokens/s✓ Runs great
OvisOCR2 0.8B0.8BQ4_K_M1.3 GB~64 tokens/s✓ Runs great
G9v3 3B3BQ4_K_M2.8 GB~20.2 tokens/s✓ Runs great
Tini Cybersec 8B-A1B8.5BQ4_K_M6.7 GB~62.7 tokens/s✓ Runs great
Ling 3.0 Tiny7.9BQ4_K_M6.3 GB~44.2 tokens/s✓ Runs great
Granite 4.2 3B3BQ4_K_M3.1 GB~17.4 tokens/s✓ Runs great
Qwen 3.5 4B4BQ4_K_M3.7 GB~14.2 tokens/s✓ Runs great
Agents-A1 4B4BQ4_K_M3.7 GB~14.2 tokens/s✓ Runs great
Nanbeige 4.2 3B4.2BQ4_K_M3.7 GB~14.2 tokens/s✓ Runs great
Nemotron 3 Nano 4B4BQ4_K_M3.8 GB~13.7 tokens/s✓ Runs great
AREX Turbo 4B4.5BQ4_K_M4 GB~13.2 tokens/s✓ Runs great
Fara 1.5 4B4.5BQ4_K_M4 GB~13.2 tokens/s✓ Runs great
Gemma 4 E2B2BQ4_K_M4 GB~12.4 tokens/s✓ Runs great
Bonsai 27B (1-bit)27BQ1_04.8 GB~10.1 tokens/s✓ Runs great
Mistral 7B v0.37.2BQ4_K_M5.7 GB~8.7 tokens/s✓ Runs great
DeepSeek R1 Distill 7B7.6BQ4_K_M6.1 GB~8.2 tokens/s✓ Runs great
Qwen3 8B8.2BQ4_K_M6.4 GB~7.7 tokens/s! Runs, barely
Llama 3.1 8B8BQ4_K_M6.3 GB~7.8 tokens/s! Runs, barely
Ministral 8B8BQ4_K_M6.3 GB~7.8 tokens/s! Runs, barely
Gemma 4 E4B4BQ4_K_M6.1 GB~7.7 tokens/s! Runs, barely
Ministral 3 8B8BQ4_K_M6.6 GB~7.4 tokens/s! Runs, barely
Granite 4.2 8B8BQ4_K_M6.7 GB~7.2 tokens/s! Runs, barely
Ornith 1.0 9B9BQ4_K_M7.1 GB~6.9 tokens/s! Runs, barely
Qwen 3.5 9B9BQ4_K_M7.2 GB~6.7 tokens/s! Runs, barely
Qwythos 9B v29BQ4_K_M7.2 GB~6.7 tokens/s! Runs, barely
GRM 3.2 Cliff 9B9.4BQ4_K_M7.5 GB~6.5 tokens/s! Runs, barely
grug 9B (ProCreations)9.4BQ4_K_M7.5 GB~6.5 tokens/s! Runs, barely
Fara 1.5 9B9.4BQ4_K_M7.5 GB~6.5 tokens/s! Runs, barely
UI-Mate 9B9BQ4_K_M7.4 GB~6.5 tokens/s! Runs, barely
Ternary Bonsai 27B27BQ2_08.4 GB~5.3 tokens/s! Runs, barely
Gemma 4 12B12BQ4_08.8 GB~5.5 tokens/s! Runs, barely
Gemma 3 12B12.2BQ4_K_M9.1 GB—✕ Won't fit
Grug 12B12BQ4_K_M9.5 GB—✕ Won't fit
Ministral 3 14B14BQ4_K_M10.2 GB—✕ Won't fit
Qwen3 14B14.8BQ4_K_M11.1 GB—✕ Won't fit
Phi-4 14B14.7BQ4_K_M11.2 GB—✕ Won't fit
GPT-OSS 20B21BMXFP414.8 GB—✕ Won't fit
Gemma 4 26B-A4B26BQ4_017.5 GB—✕ Won't fit
Qwen3 30B A3B30.5BQ4_K_M22.3 GB—✕ Won't fit
Qwen 3.5 27B27BQ4_K_M20 GB—✕ Won't fit
Qwen 3.5 35B-A3B35BQ4_K_M26.2 GB—✕ Won't fit
Qwen 3.6 27B27BQ4_K_M18.5 GB—✕ Won't fit
Qwen 3.6 35B-A3B35BQ4_K_M23.9 GB—✕ Won't fit
Nemotron 3 Nano 30B-A3B30BQ4_K_M28.5 GB—✕ Won't fit
Nemotron 3 Nano Omni 30B-A3B31BQ4_K_M26.3 GB—✕ Won't fit
Nemotron 3.5 Lightning 30B-A3B30BQ8_035.9 GB—✕ Won't fit
Ornith 1.0 35B-A3B35BQ4_K_M25.3 GB—✕ Won't fit
XYZ-Aquila mini 35B-A3B35BQ4_K_M25.5 GB—✕ Won't fit
Salience 1.5 Flash30BQ4_K_M22.3 GB—✕ Won't fit
Fara 1.5 27B27BQ4_K_M20.9 GB—✕ Won't fit
KAT-Coder V2.5 Dev35BQ4_K_M25.5 GB—✕ Won't fit
BigBang V1 36B-A3B36BQ4_K_M26.1 GB—✕ Won't fit
Muse Glimmer 30B29.6BK_QUANT_17GB20.3 GB—✕ Won't fit
Qwen3.8 27B27BQ4_K_M20.8 GB—✕ Won't fit
Qwen3.8 2.4T-A95B2400BIQ4_XS1377.4 GB—✕ Won't fit
UI-Mate 27B27BQ4_K_M20.9 GB—✕ Won't fit
GLM-4.5V106BQ4_K_M74.8 GB—✕ Won't fit
GLM-4.5-Air106BQ4_K_M74.8 GB—✕ Won't fit
Granite 4.2 30B30BQ4_K_M21.3 GB—✕ Won't fit
Apodex 1.1 Mini35BQ4_K_M26 GB—✕ Won't fit
Ling 3.0 Flash124BQ4_K_M82.3 GB—✕ Won't fit
Qwen3.8-Flash-Next125BIQ4_XS107.7 GB—✕ Won't fit
GLM-5.3744BQ4_K_XL543.3 GB—✕ Won't fit
GLM-5.3-Flash320BQ4_K_XL232.7 GB—✕ Won't fit
Llama 3.3 70B70BQ4_K_M50.1 GB—✕ Won't fit
Qwen3 32B32.8BQ4_K_M23.7 GB—✕ Won't fit
Ornith 1.0 397B397BQ4_K_M285.6 GB—✕ Won't fit
Gemma 4 31B31BQ4_K_M22 GB—✕ Won't fit
Hunyuan 3 (Hy3)298.8BQ4_K_M212.8 GB—✕ Won't fit
DeepSeek V4 Flash 0731284BQ4_K_XL163.6 GB—✕ Won't fit
Inkling952.4BQ8_0966.9 GB—✕ Won't fit
Inkling Small276BQ4_K_M190.5 GB—✕ Won't fit
LongCat Flash Chat561.9BIQ1_S159.6 GB—✕ Won't fit
Laguna XS 2.133BQ4_K_M24.2 GB—✕ Won't fit
Laguna S 2.1118BQ4_K_M109.7 GB—✕ Won't fit

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

Best model by use case

Best for Chat
Qwen3 0.6B

Top everyday assistant & writing pick here — ~64 tokens/s at Q8_0, using 1.3 of ~9GB.

Best for Coding
Qwen3 4B

Top code completion & explain-this pick here — ~15.4 tokens/s at Q4_K_M, using 3.5 of ~9GB.

Best for Reasoning
Phi-4 Mini 3.8B

Top math & step-by-step thinking pick here — ~15.4 tokens/s at Q4_K_M, using 3.5 of ~9GB.

FAQ

What is the biggest AI model the Galaxy Z Flip8 can run?

Bonsai 27B (1-bit) (27B parameters) at Q1_0 — it needs 4.8GB of the ~9GB usable on the 12GB Galaxy Z Flip8 and runs at ~10.1 tokens/s.

How much of the Galaxy Z Flip8's 12GB RAM can AI models actually use?

About 9GB. Android keeps roughly 2–4GB for the system and resident apps, so of the 12GB about 9GB is actually available to a model.

Can the Galaxy Z Flip8 run Llama 3.1 8B?

Yes — at Q4_K_M it needs 6.3GB of the ~9GB usable and runs at ~7.8 tokens/s.

How fast is local AI on the Galaxy Z Flip8?

The Samsung Exynos 2600 has 85.3GB/s of memory bandwidth, which is what decode speed scales with. Small models like Ternary Bonsai 1.7B reach ~76.8 tokens/s; larger 7–14B models land in the single digits. Anything above ~8 tokens/s feels smooth for chat.

Which quantization should I use on the Galaxy Z Flip8?

Q4_K_M is the size/quality sweet spot for most models. For example, Qwen3 0.6B at Q8_0 takes 1.3GB of memory here. Only drop to Q3 or IQ4 if a model just misses fitting; Q8 rarely pays off on 12GB of RAM.

Is 12GB of RAM enough for local AI?

49 of the 93 models we track fit on the Galaxy Z Flip8 — 34 run great and 15 run with compromises. 44 models (mostly 12B+) don't fit at their recommended quant.

Other Samsung phones

Galaxy S25 UltraGalaxy S25Galaxy S24 UltraGalaxy S24Galaxy S23 UltraGalaxy A55Galaxy S26Galaxy S26+Galaxy S26 UltraGalaxy S26 FEGalaxy S25 FEGalaxy A16 5GGalaxy A17 5GGalaxy A26 5GGalaxy A36 5GGalaxy A56 5GGalaxy Z Fold6Galaxy Z Flip6Galaxy Z Fold7Galaxy Z Flip7Galaxy A57 5GGalaxy A37 5GGalaxy Z Fold8Galaxy Z Fold8 UltraGalaxy Z Fold5Galaxy Z Flip5