FitMyLLM
NVIDIA/ Ampere

NVIDIA GeForce RTX 3050 8 GB

8 GB
VRAM (Entry-level)
224 GB/s
Memory Bandwidth
147 / 290
Models fit at Q4 (51%)
~26 tok/s
7B Q4 speed (Good)
Model coverage at Q451% of all models

Specifications

VRAM
8 GB
Bandwidth
224 GB/s
FP16 Compute
9.1 TFLOPS
TDP
130W
Memory
GDDR6
Architecture
Ampere
CUDA Cores
2,560
Tensor Cores
80
PCIe
Gen 4 x8
MSRP
$249
68
Fast models (>30 tok/s)
Real-time chat speed
147
Usable models (>10 tok/s)
Comfortable for all tasks
147
Total compatible
Fit in VRAM at Q4

Where to Buy

AmazonNewegg

MSRP: $249

Compatible Models(147)

S
GPT-2 124M0.124B
gpt21K ctxchat
1445
tok/s
5% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
1327
tok/s
5% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
1308
tok/s
3% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
535
tok/s
5% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
535
tok/s
5% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
519
tok/s
6% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
498
tok/s
6% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
358
tok/s
10% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
358
tok/s
10% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
315
tok/s
8% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
299
tok/s
8% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
232
tok/s
9% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
224
tok/s
12% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
199
tok/s
12% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
179
tok/s
13% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
179
tok/s
13% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
163
tok/s
14% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
163
tok/s
14% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
149
tok/s
15% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
149
tok/s
9% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
138
tok/s
15% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
138
tok/s
15% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
138
tok/s
15% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
138
tok/s
15% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
119
tok/s
16% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
119
tok/s
17% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
119
tok/s
17% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
119
tok/s
17% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
119
tok/s
17% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
112
tok/s
17% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
105
tok/s
18% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
105
tok/s
17% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
100
tok/s
19% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
94
tok/s
17% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
90
tok/s
55% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
90
tok/s
20% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
90
tok/s
20% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
90
tok/s
20% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
81
tok/s
21% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
78
tok/s
22% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce RTX 3050 8 GB.

Find Models for GeForce RTX 3050 8 GBCompare with other GPUs