FitMyLLM
NVIDIA/ Ampere

NVIDIA GeForce RTX 3080 Ti

12 GB
VRAM (Entry-level)
912 GB/s
Memory Bandwidth
182 / 290
Models fit at Q4 (63%)
~104 tok/s
7B Q4 speed (Blazing)
Model coverage at Q463% of all models

Specifications

VRAM
12 GB
Bandwidth
912 GB/s
FP16 Compute
34.1 TFLOPS
TDP
350W
Memory
GDDR6X
Architecture
Ampere
CUDA Cores
10,240
Tensor Cores
320
PCIe
Gen 4 x16
MSRP
$1,199
182
Fast models (>30 tok/s)
Real-time chat speed
182
Usable models (>10 tok/s)
Comfortable for all tasks
182
Total compatible
Fit in VRAM at Q4

Where to Buy

AmazoneBay

MSRP: $1,199

Compatible Models(182)

S
GPT-2 124M0.124B
gpt21K ctxchat
5884
tok/s
3% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
5404
tok/s
3% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
5326
tok/s
2% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
2178
tok/s
4% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
2178
tok/s
4% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
2115
tok/s
4% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
2027
tok/s
4% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
1459
tok/s
6% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
1459
tok/s
6% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
1285
tok/s
5% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
1216
tok/s
5% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
943
tok/s
6% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
912
tok/s
8% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
811
tok/s
8% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
730
tok/s
8% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
730
tok/s
8% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
663
tok/s
9% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
663
tok/s
9% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
608
tok/s
10% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
608
tok/s
6% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
561
tok/s
10% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
561
tok/s
10% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
561
tok/s
10% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
561
tok/s
10% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
486
tok/s
11% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
486
tok/s
11% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
486
tok/s
11% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
486
tok/s
11% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
486
tok/s
11% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
456
tok/s
12% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
429
tok/s
12% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
427
tok/s
12% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
405
tok/s
13% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
384
tok/s
11% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
365
tok/s
37% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
365
tok/s
13% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
365
tok/s
13% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
365
tok/s
13% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
330
tok/s
14% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
317
tok/s
15% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce RTX 3080 Ti.

Find Models for GeForce RTX 3080 TiCompare with other GPUs