FitMyLLM
NVIDIA/ Turing

NVIDIA Quadro RTX 3000 Mobile Refresh

6 GB
VRAM (Budget)
336 GB/s
Memory Bandwidth
134 / 290
Models fit at Q4 (46%)
~38 tok/s
7B Q4 speed (Fast)
Model coverage at Q446% of all models

Specifications

VRAM
6 GB
Bandwidth
336 GB/s
FP16 Compute
10.6 TFLOPS
TDP
80W
Memory
GDDR6
Architecture
Turing
CUDA Cores
1,920
Tensor Cores
240
PCIe
Gen 3 x16
134
Fast models (>30 tok/s)
Real-time chat speed
134
Usable models (>10 tok/s)
Comfortable for all tasks
134
Total compatible
Fit in VRAM at Q4

Compatible Models(134)

S
GPT-2 124M0.124B
gpt21K ctxchat
2168
tok/s
6% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
1991
tok/s
6% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
1962
tok/s
5% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
802
tok/s
7% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
802
tok/s
7% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
779
tok/s
8% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
747
tok/s
8% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
538
tok/s
13% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
538
tok/s
13% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
473
tok/s
10% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
448
tok/s
11% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
347
tok/s
12% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
336
tok/s
16% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
299
tok/s
17% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
269
tok/s
17% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
269
tok/s
17% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
244
tok/s
18% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
244
tok/s
18% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
224
tok/s
19% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
224
tok/s
12% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
207
tok/s
20% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
207
tok/s
20% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
207
tok/s
20% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
207
tok/s
20% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
179
tok/s
21% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
179
tok/s
22% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
179
tok/s
22% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
179
tok/s
22% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
179
tok/s
22% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
168
tok/s
23% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
158
tok/s
23% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
157
tok/s
23% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
149
tok/s
25% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
141
tok/s
23% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
134
tok/s
74% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
134
tok/s
27% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
134
tok/s
26% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
134
tok/s
26% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
122
tok/s
28% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
117
tok/s
30% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Quadro RTX 3000 Mobile Refresh.

Find Models for Quadro RTX 3000 Mobile RefreshCompare with other GPUs