AI Models for vivo Y600i — What runs on 6GB

5 great · 24 slow · 72 won't fit

Chip

Snapdragon 4 Gen 2

Memory bandwidth

17.1 GB/s

NPU

—

RAM options

6 GB

Usable for models

~4 GB

Year

2026

Specs checked against manufacturer and public documentation on 2026-09-26. China.

What runs on the vivo Y600i

All 101 models at their recommended quant, on the 6GB configuration. Select any row for the full report.

Model	Params	Quant	Needs	Speed	Verdict
Ternary Bonsai 1.7B	1.7B	Q2_0	1.2 GB	~15.4 tokens/s	✓ Runs great
Qwen3 0.6B	0.6B	Q8_0	1.3 GB	~12.8 tokens/s	✓ Runs great
OvisOCR2 0.8B	0.8B	Q4_K_M	1.3 GB	~12.8 tokens/s	✓ Runs great
Llama 3.2 1B	1.2B	Q4_K_M	1.5 GB	~9.6 tokens/s	✓ Runs great
Gemma 3 1B	1B	Q4_K_M	1.5 GB	~9.6 tokens/s	✓ Runs great
DeepSeek R1 Distill 1.5B	1.8B	Q4_K_M	1.9 GB	~7 tokens/s	! Runs, barely
SmolLM2 1.7B	1.7B	Q4_K_M	1.9 GB	~7 tokens/s	! Runs, barely
Ternary Bonsai 4B	4B	Q2_0	2 GB	~7 tokens/s	! Runs, barely
Qwen 3.5 2B	2B	Q4_K_M	2.1 GB	~5.9 tokens/s	! Runs, barely
MiniCPM5-2B	2.52B	Q4_K_M	2.5 GB	~4.8 tokens/s	! Runs, barely
LFM2.5 2.6B	2.7B	Q4_K_M	2.6 GB	~4.5 tokens/s	! Runs, barely
LFM2.5-VL 3B	3.1B	Q4_K_M	2.6 GB	~4.5 tokens/s	! Runs, barely
Qwen3 1.7B	1.7B	Q8_0	2.6 GB	~4.3 tokens/s	! Runs, barely
SmolLM3 3B	3.1B	Q4_K_M	2.8 GB	~4.1 tokens/s	! Runs, barely
G9v3 3B	3B	Q4_K_M	2.8 GB	~4.1 tokens/s	! Runs, barely
Llama 3.2 3B	3.2B	Q4_K_M	2.9 GB	~3.8 tokens/s	! Runs, barely
Ministral 3 3B	3B	Q4_K_M	3 GB	~3.7 tokens/s	! Runs, barely
Granite 4.2 3B	3B	Q4_K_M	3.1 GB	~3.5 tokens/s	! Runs, barely
Ternary Bonsai 8B	8B	Q2_0	3.5 GB	~3.5 tokens/s	! Runs, barely
Qwen3 4B	4B	Q4_K_M	3.5 GB	~3.1 tokens/s	! Runs, barely
Gemma 3 4B	4.3B	Q4_K_M	3.5 GB	~3.1 tokens/s	! Runs, barely
Phi-4 Mini 3.8B	3.8B	Q4_K_M	3.5 GB	~3.1 tokens/s	! Runs, barely
Qwen 3.5 4B	4B	Q4_K_M	3.7 GB	~2.9 tokens/s	! Runs, barely
Agents-A1 4B	4B	Q4_K_M	3.7 GB	~2.9 tokens/s	! Runs, barely
Nanbeige 4.2 3B	4.2B	Q4_K_M	3.7 GB	~2.9 tokens/s	! Runs, barely
Nemotron 3 Nano 4B	4B	Q4_K_M	3.8 GB	~2.7 tokens/s	! Runs, barely
AREX Turbo 4B	4.5B	Q4_K_M	4 GB	~2.7 tokens/s	! Runs, barely
Fara 1.5 4B	4.5B	Q4_K_M	4 GB	~2.7 tokens/s	! Runs, barely
Gemma 4 E2B	2B	Q4_K_M	4 GB	~2.5 tokens/s	! Runs, barely
Bonsai 27B (1-bit)	27B	Q1_0	4.8 GB	—	✕ Won't fit
Mistral 7B v0.3	7.2B	Q4_K_M	5.7 GB	—	✕ Won't fit
DeepSeek R1 Distill 7B	7.6B	Q4_K_M	6.1 GB	—	✕ Won't fit
Gemma 4 E4B	4B	Q4_K_M	6.1 GB	—	✕ Won't fit
Llama 3.1 8B	8B	Q4_K_M	6.3 GB	—	✕ Won't fit
Ministral 8B	8B	Q4_K_M	6.3 GB	—	✕ Won't fit
Ling 3.0 Tiny	7.9B	Q4_K_M	6.3 GB	—	✕ Won't fit
Qwen3 8B	8.2B	Q4_K_M	6.4 GB	—	✕ Won't fit
Ministral 3 8B	8B	Q4_K_M	6.6 GB	—	✕ Won't fit
LFM2.5 8B-A1B	8B	Q4_K_M	6.6 GB	—	✕ Won't fit
Tini Cybersec 8B-A1B	8.5B	Q4_K_M	6.7 GB	—	✕ Won't fit
Granite 4.2 8B	8B	Q4_K_M	6.7 GB	—	✕ Won't fit
Ornith 1.0 9B	9B	Q4_K_M	7.1 GB	—	✕ Won't fit
Qwen 3.5 9B	9B	Q4_K_M	7.2 GB	—	✕ Won't fit
Qwythos 9B v2	9B	Q4_K_M	7.2 GB	—	✕ Won't fit
LensVLM 9B	9.4B	Q4_K_M	7.3 GB	—	✕ Won't fit
GRM 3.2 Cliff 9B	9.4B	Q4_K_M	7.5 GB	—	✕ Won't fit
grug 9B (ProCreations)	9.4B	Q4_K_M	7.5 GB	—	✕ Won't fit
Fara 1.5 9B	9.4B	Q4_K_M	7.5 GB	—	✕ Won't fit
UI-Mate 9B	9B	Q4_K_M	7.4 GB	—	✕ Won't fit
Qwen3 14B	14.8B	Q4_K_M	11.1 GB	—	✕ Won't fit
Qwen3 30B A3B	30.5B	Q4_K_M	22.3 GB	—	✕ Won't fit
Gemma 3 12B	12.2B	Q4_K_M	9.1 GB	—	✕ Won't fit
Phi-4 14B	14.7B	Q4_K_M	11.2 GB	—	✕ Won't fit
MiMo V2.6 Distill Qwen 9B	9.4B	Q8_0	11.2 GB	—	✕ Won't fit
Qwen 3.5 27B	27B	Q4_K_M	20 GB	—	✕ Won't fit
Qwen 3.5 35B-A3B	35B	Q4_K_M	26.2 GB	—	✕ Won't fit
Qwen 3.6 27B	27B	Q4_K_M	18.5 GB	—	✕ Won't fit
Qwen 3.6 35B-A3B	35B	Q4_K_M	23.9 GB	—	✕ Won't fit
Gemma 4 12B	12B	Q4_0	8.8 GB	—	✕ Won't fit
Gemma 4 26B-A4B	26B	Q4_0	17.5 GB	—	✕ Won't fit
Ternary Bonsai 27B	27B	Q2_0	8.4 GB	—	✕ Won't fit
Nemotron 3 Nano 30B-A3B	30B	Q4_K_M	28.5 GB	—	✕ Won't fit
Nemotron 3 Nano Omni 30B-A3B	31B	Q4_K_M	26.3 GB	—	✕ Won't fit
Nemotron 3.5 Lightning 30B-A3B	30B	Q8_0	35.9 GB	—	✕ Won't fit
Ministral 3 14B	14B	Q4_K_M	10.2 GB	—	✕ Won't fit
GPT-OSS 20B	21B	MXFP4	14.8 GB	—	✕ Won't fit
Ornith 1.0 35B-A3B	35B	Q4_K_M	25.3 GB	—	✕ Won't fit
Grug 12B	12B	Q4_K_M	9.5 GB	—	✕ Won't fit
XYZ-Aquila mini 35B-A3B	35B	Q4_K_M	25.5 GB	—	✕ Won't fit
Salience 1.5 Flash	30B	Q4_K_M	22.3 GB	—	✕ Won't fit
Fara 1.5 27B	27B	Q4_K_M	20.9 GB	—	✕ Won't fit
KAT-Coder V2.5 Dev	35B	Q4_K_M	25.5 GB	—	✕ Won't fit
BigBang V1 36B-A3B	36B	Q4_K_M	26.1 GB	—	✕ Won't fit
Muse Glimmer 30B	29.6B	K_QUANT_17GB	20.3 GB	—	✕ Won't fit
Qwen3.8 27B	27B	Q4_K_M	20.8 GB	—	✕ Won't fit
Qwen3.8 2.4T-A95B	2400B	IQ4_XS	1377.4 GB	—	✕ Won't fit
UI-Mate 27B	27B	Q4_K_M	20.9 GB	—	✕ Won't fit
GLM-4.5V	106B	Q4_K_M	74.8 GB	—	✕ Won't fit
GLM-4.5-Air	106B	Q4_K_M	74.8 GB	—	✕ Won't fit
Granite 4.2 30B	30B	Q4_K_M	21.3 GB	—	✕ Won't fit
Apodex 1.1 Mini	35B	Q4_K_M	26 GB	—	✕ Won't fit
Ling 3.0 Flash	124B	Q4_K_M	82.3 GB	—	✕ Won't fit
Ling 3.0 Flash Fin	124B	Q4_K_M	91 GB	—	✕ Won't fit
Ling 3.0 Flash VL	124.85B	Q4_K_M	92 GB	—	✕ Won't fit
Swift 1.5 Qwen3.8 27B	27.8B	Q4_K_M	20.8 GB	—	✕ Won't fit
Swift 1.5 Qwen3.8 Flash Next	125B	Q2_0	79.2 GB	—	✕ Won't fit
Qwen3.8-Flash-Next	125B	IQ4_XS	107.7 GB	—	✕ Won't fit
GLM-5.3	744B	Q4_K_XL	543.3 GB	—	✕ Won't fit
GLM-5.3-Flash	320B	Q4_K_XL	232.7 GB	—	✕ Won't fit
Llama 3.3 70B	70B	Q4_K_M	50.1 GB	—	✕ Won't fit
Qwen3 32B	32.8B	Q4_K_M	23.7 GB	—	✕ Won't fit
Ornith 1.0 397B	397B	Q4_K_M	285.6 GB	—	✕ Won't fit
Gemma 4 31B	31B	Q4_K_M	22 GB	—	✕ Won't fit
Hunyuan 3 (Hy3)	298.8B	Q4_K_M	212.8 GB	—	✕ Won't fit
DeepSeek V4 Flash 0731	284B	Q4_K_XL	163.6 GB	—	✕ Won't fit
DeepSeek V4 Flash Vision Exp	284B	Q4_K_XL	183.3 GB	—	✕ Won't fit
Inkling	952.4B	Q8_0	966.9 GB	—	✕ Won't fit
Inkling Small	276B	Q4_K_M	190.5 GB	—	✕ Won't fit
LongCat Flash Chat	561.9B	IQ1_S	159.6 GB	—	✕ Won't fit
Laguna XS 2.1	33B	Q4_K_M	24.2 GB	—	✕ Won't fit
Laguna S 2.1	118B	Q4_K_M	109.7 GB	—	✕ Won't fit

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

Best model by use case

Best for Chat

Ternary Bonsai 1.7B

Top everyday assistant & writing pick here — ~15.4 tokens/s at Q2_0, using 1.2 of ~4GB.

Best for Coding

MiniCPM5-2B

Top code completion & explain-this pick here — ~4.8 tokens/s at Q4_K_M, using 2.5 of ~4GB.

Best for Reasoning

DeepSeek R1 Distill 1.5B

Top math & step-by-step thinking pick here — ~7 tokens/s at Q4_K_M, using 1.9 of ~4GB.

FAQ

What is the biggest AI model the vivo Y600i can run?

Ternary Bonsai 8B (8B parameters) at Q2_0 — it needs 3.5GB of the ~4GB usable on the 6GB vivo Y600i, at ~3.5 tokens/s.

How much of the vivo Y600i's 6GB RAM can AI models actually use?

About 4GB. Android keeps roughly 2–4GB for the system and resident apps, so of the 6GB about 4GB is actually available to a model.

Can the vivo Y600i run Llama 3.1 8B?

Not at Q4_K_M: it needs 6.3GB but the vivo Y600i only has ~4GB usable. Try a smaller model like Ternary Bonsai 1.7B.

How fast is local AI on the vivo Y600i?

The Snapdragon 4 Gen 2 has 17.1GB/s of memory bandwidth, which is what decode speed scales with. Small models like Ternary Bonsai 1.7B reach ~15.4 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 vivo Y600i?

Q4_K_M is the size/quality sweet spot for most models. For example, Ternary Bonsai 1.7B at Q2_0 takes 1.2GB of memory here. Only drop to Q3 or IQ4 if a model just misses fitting; Q8 rarely pays off on 6GB of RAM.

Is 6GB of RAM enough for local AI?

29 of the 101 models we track fit on the vivo Y600i — 5 run great and 24 run with compromises. 72 models (mostly 12B+) don't fit at their recommended quant.

Other vivo phones

vivo X200 Pro vivo X100 Pro vivo X300 Pro vivo X500 Pro vivo X500 Pro Max vivo X300 E vivo X Fold3 vivo X Fold3 Pro vivo X Fold5 vivo X Fold6 vivo S2 vivo V80 Lite 5G (Pakistan)