FitMyLLM
NVIDIA/ Blackwell 2.0

NVIDIA GeForce RTX 5070 Ti

16 GB
VRAM (Mid-range)
896 GB/s
Memory Bandwidth
191 / 290
Models fit at Q4 (66%)
~102 tok/s
7B Q4 speed (Blazing)
Model coverage at Q466% of all models

Specifications

VRAM
16 GB
Bandwidth
896 GB/s
FP16 Compute
43.9 TFLOPS
TDP
300W
Memory
GDDR7
Architecture
Blackwell 2.0
CUDA Cores
8,960
Tensor Cores
280
PCIe
Gen 5 x16
MSRP
$749
191
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

NVIDIA StoreAmazonNeweggBest Buy

MSRP: $749

Compatible Models(191)

S
GPT-2 124M0.124B
gpt21K ctxchat
5781
tok/s
2% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
5310
tok/s
2% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
5232
tok/s
2% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
2140
tok/s
3% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
2140
tok/s
3% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
2078
tok/s
3% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
1991
tok/s
3% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
1434
tok/s
5% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
1434
tok/s
5% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
1262
tok/s
4% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
1195
tok/s
4% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
926
tok/s
5% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
896
tok/s
6% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
796
tok/s
6% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
717
tok/s
6% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
717
tok/s
6% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
652
tok/s
7% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
652
tok/s
7% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
597
tok/s
7% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
597
tok/s
4% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
551
tok/s
8% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
551
tok/s
7% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
551
tok/s
8% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
551
tok/s
8% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
478
tok/s
8% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
478
tok/s
8% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
478
tok/s
8% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
478
tok/s
8% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
478
tok/s
8% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
448
tok/s
9% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
422
tok/s
9% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
419
tok/s
9% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
398
tok/s
9% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
377
tok/s
9% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
358
tok/s
28% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
358
tok/s
10% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
358
tok/s
10% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
358
tok/s
10% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
324
tok/s
11% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
312
tok/s
11% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce RTX 5070 Ti.

Find Models for GeForce RTX 5070 TiCompare with other GPUs