ASUS ROG Strix G16 (RTX 4070 Laptop)

Windows

ROG Strix G16 with GeForce RTX 4070 Laptop GPU (80W class), 32GB RAM (representative SKU).

From

$1,899

You'll be taken to ASUS to complete your purchase.

Buy on ASUS

Memory

8 GB

GPUs

1×

RAM

32 GB

Models

Type

Laptop

Inference Memory

8 GB

Accelerator

8 GB GDDR6

System RAM

32 GB

CPU

Intel Core i9-14900HX

Windows

Laptop Performance Note

Laptop GPU performance varies by cooling and power limits. Listed tok/s reflect sustained loads, not short bursts; your unit may differ.

What it can run

52 models


all-MiniLM-L6-v2	FP16	5950 tok/s	Excellent
Arcee Trinity Nano 6B	Q8_0	45 tok/s	Excellent
Code Llama 34B Instruct	Q2_K	–	Not viable
Codestral 22B	Q3_K_M	–	Not viable
Command R 35B	Q2_K	–	Not viable
DeepSeek Coder V2 Lite 16B	Q3_K_M	31 tok/s	Good
DeepSeek R1 Distill Qwen 32B	Q2_K	–	Not viable
DeepSeek R1 Distill Qwen 7B	Q4_K_M	22 tok/s	Acceptable
DeepSeek V3	Q2_K	–	Not viable
FLUX.1 Dev	Q4_K_M	–	Marginal
Gemma 2 27B Instruct	Q3_K_M	–	Not viable
Gemma 2 9B Instruct	Q4_K_M	20 tok/s	Acceptable
Gemma 3 12B	Q3_K_M	13 tok/s	Acceptable
Gemma 3 27B	Q3_K_M	–	Not viable
Gemma 3 4B	Q5_K_M	39 tok/s	Good
Gemma 4 E2B	Q8_0	38 tok/s	Good
Gemma 4 E4B	Q6_K	30 tok/s	Good
GigaChat Lightning 10B	Q4_K_M	56 tok/s	Acceptable
InternLM 2.5 7B Chat	Q4_K_M	21 tok/s	Acceptable
Llama 3.1 70B Instruct	Q2_K	–	Not viable
Llama 3.1 8B Instruct	Q4_K_M	22 tok/s	Acceptable
Llama 3.2 1B Instruct	Q8_0	67 tok/s	Excellent
Llama 3.2 3B Instruct	Q8_0	46 tok/s	Good
Llama 3.3 70B Instruct	Q2_K	–	Not viable
LLaVA 1.6 13B	Q3_K_M	15 tok/s	Acceptable
Mistral 7B Instruct v0.3	Q4_K_M	22 tok/s	Acceptable
Mistral Small 24B Instruct	Q3_K_M	–	Not viable
Mixtral 8x7B Instruct	Q4_K_M	–	Not viable
nomic-embed-text v1.5	Q8_0	2940 tok/s	Excellent
NVIDIA Nemotron-3-super-120B-A12B	Q2_K	–	Not viable
Phi-3 Medium 14B Instruct	Q3_K_M	14 tok/s	Acceptable
Phi-3 Mini 3.8B Instruct	Q5_K_M	36 tok/s	Good
Phi-4 14B	Q3_K_M	13 tok/s	Acceptable
Phi-4 Mini	Q5_K_M	39 tok/s	Good
Qwen 2.5 14B Instruct	Q3_K_M	12 tok/s	Acceptable
Qwen 2.5 72B Instruct	Q2_K	–	Not viable
Qwen 2.5 7B Instruct	Q4_K_M	21 tok/s	Acceptable
Qwen 2.5 Coder 32B Instruct	Q2_K	–	Not viable
Qwen 2.5 Coder 7B Instruct	Q4_K_M	22 tok/s	Acceptable
Qwen3-14B Instruct	Q3_K_M	13 tok/s	Acceptable
Qwen3-8B Instruct	Q5_K_M	16 tok/s	Acceptable
Qwen3.5-27B	Q3_K_M	–	Not viable
Qwen3.5-397B (MoE)	Q2_K	–	Not viable
Qwen3.6-27B	Q3_K_M	–	Not viable
QwQ 32B Preview	Q2_K	–	Not viable
Stable Diffusion 3 Medium	FP16	–	Good
Stable Diffusion 3.5 Large	Q8_0	–	Not viable
Stable Diffusion XL 1.0	FP16	–	Good
StarCoder 2 15B	Q3_K_M	11 tok/s	Acceptable
Whisper Large V3	Q5_K_M	–	Excellent
Whisper Large V3 Turbo	FP16	–	Excellent
Yi 1.5 34B Chat	Q2_K	–	Not viable

Showing 52 of 52 entries

Best Fit

Who this machine makes sense for

This machine is best for people who need portable local AI and are willing to trade some sustained throughput for mobility. 8 GB is enough to make the form factor relevant, not just convenient.

Before You Buy

What to verify first

Pay attention to sustained power limits, fan noise, and battery-mode behavior. Laptop AI performance is often bounded by cooling and power policy more than spec-sheet peak numbers.

All machines