FitMyLLM
NVIDIA/ Ada Lovelace

NVIDIA GeForce RTX 4070 Ti SUPER AD102

16 GB
VRAM (Mid-range)
672 GB/s
Memory Bandwidth
191 / 290
Models fit at Q4 (66%)
~77 tok/s
7B Q4 speed (Blazing)
Model coverage at Q466% of all models

Specifications

VRAM
16 GB
Bandwidth
672 GB/s
FP16 Compute
44.1 TFLOPS
TDP
285W
Memory
GDDR6X
Architecture
Ada Lovelace
CUDA Cores
8,448
Tensor Cores
264
PCIe
Gen 4 x16
MSRP
$799
183
Fast models (>30 tok/s)
Real-time chat speed
191
Usable models (>10 tok/s)
Comfortable for all tasks
191
Total compatible
Fit in VRAM at Q4

Where to Buy

AmazonNeweggBest Buy

MSRP: $799

Compatible Models(191)

S
GPT-2 124M0.124B
gpt21K ctxchat
4335
tok/s
2% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
3982
tok/s
2% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
3924
tok/s
2% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
1605
tok/s
3% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
1605
tok/s
3% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
1558
tok/s
3% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
1493
tok/s
3% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
1075
tok/s
5% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
1075
tok/s
5% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
946
tok/s
4% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
896
tok/s
4% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
695
tok/s
5% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
672
tok/s
6% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
597
tok/s
6% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
538
tok/s
6% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
538
tok/s
6% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
489
tok/s
7% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
489
tok/s
7% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
448
tok/s
7% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
448
tok/s
4% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
414
tok/s
8% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
414
tok/s
7% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
414
tok/s
8% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
414
tok/s
8% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
358
tok/s
8% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
358
tok/s
8% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
358
tok/s
8% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
358
tok/s
8% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
358
tok/s
8% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
336
tok/s
9% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
316
tok/s
9% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
314
tok/s
9% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
299
tok/s
9% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
283
tok/s
9% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
269
tok/s
28% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
269
tok/s
10% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
269
tok/s
10% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
269
tok/s
10% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
243
tok/s
11% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
234
tok/s
11% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce RTX 4070 Ti SUPER AD102.

Find Models for GeForce RTX 4070 Ti SUPER AD102Compare with other GPUs