FitMyLLM
NVIDIA/ Kepler

NVIDIA GeForce GTX 675MX

2 GB
VRAM (Budget)
115 GB/s
Memory Bandwidth
39 / 290
Models fit at Q4 (13%)
~13 tok/s
7B Q4 speed (Usable)
Model coverage at Q413% of all models

Specifications

VRAM
2 GB
Bandwidth
115 GB/s
FP16 Compute
1.3 TFLOPS
TDP
100W
Memory
GDDR5
Architecture
Kepler
CUDA Cores
960
39
Fast models (>30 tok/s)
Real-time chat speed
39
Usable models (>10 tok/s)
Comfortable for all tasks
39
Total compatible
Fit in VRAM at Q4

Compatible Models(39)

S
GPT-2 124M0.124B
gpt21K ctxchat
742
tok/s
18% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
681
tok/s
18% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
672
tok/s
14% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
275
tok/s
22% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
275
tok/s
22% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
267
tok/s
24% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
256
tok/s
25% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
184
tok/s
38% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
184
tok/s
38% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
162
tok/s
30% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
153
tok/s
32% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
119
tok/s
36% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
115
tok/s
47% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
102
tok/s
50% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
92
tok/s
50% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
92
tok/s
50% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
84
tok/s
55% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
84
tok/s
55% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
77
tok/s
58% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
77
tok/s
36% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
71
tok/s
61% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
71
tok/s
59% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
71
tok/s
61% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
71
tok/s
61% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
61
tok/s
64% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
61
tok/s
67% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
61
tok/s
67% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
61
tok/s
67% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
61
tok/s
67% VRAM
A
stablelm-2-1_6b1.6B
stablelm4K ctxchat
58
tok/s
69% VRAM
A
SmolLM2 1.7B1.71B
smollm8K ctxchat
54
tok/s
70% VRAM
A
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
54
tok/s
70% VRAM
A
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
51
tok/s
75% VRAM
A
Moondream2 1.9B1.9B
other2K ctxvisionchat
48
tok/s
68% VRAM
A
Gemma 1 2B2B
gemma8K ctxchat
46
tok/s
81% VRAM
A
Granite 3.0 2B2B
granite128K ctxchatcoding
46
tok/s
78% VRAM
A
Granite 3.1 2B2B
granite128K ctxchatcoding
46
tok/s
78% VRAM
A
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
42
tok/s
84% VRAM
A
Qwen3.5-2B2.3B
qwen256K ctxchat
40
tok/s
89% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce GTX 675MX.

Find Models for GeForce GTX 675MXCompare with other GPUs