FitMyLLM
APPLE/ M3 Pro

Apple M3 Pro (36GB)

36 GB
VRAM (High-end)
150 GB/s
Memory Bandwidth
237 / 290
Models fit at Q4 (82%)
~19 tok/s
7B Q4 speed (Good)
Model coverage at Q482% of all models

Specifications

VRAM
36 GB
Bandwidth
150 GB/s
FP16 Compute
14.2 TFLOPS
TDP
30W
Memory
LPDDR5
Architecture
M3 Pro
MSRP
$1,999
72
Fast models (>30 tok/s)
Real-time chat speed
188
Usable models (>10 tok/s)
Comfortable for all tasks
237
Total compatible
Fit in VRAM at Q4

Compatible Models(237)

S
GPT-2 124M0.124B
gpt21K ctxchat
1075
tok/s
1% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
988
tok/s
1% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
973
tok/s
1% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
398
tok/s
1% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
398
tok/s
1% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
386
tok/s
1% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
370
tok/s
1% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
267
tok/s
2% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
267
tok/s
2% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
235
tok/s
2% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
222
tok/s
2% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
172
tok/s
2% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
167
tok/s
3% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
148
tok/s
3% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
133
tok/s
3% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
133
tok/s
3% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
121
tok/s
3% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
121
tok/s
3% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
111
tok/s
3% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
111
tok/s
2% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
103
tok/s
3% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
103
tok/s
3% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
103
tok/s
3% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
103
tok/s
3% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
89
tok/s
4% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
89
tok/s
4% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
89
tok/s
4% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
89
tok/s
4% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
89
tok/s
4% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
83
tok/s
4% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
78
tok/s
4% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
78
tok/s
4% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
74
tok/s
4% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
70
tok/s
4% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
67
tok/s
12% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
67
tok/s
4% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
67
tok/s
4% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
67
tok/s
4% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
60
tok/s
5% VRAM
A
Qwen3.5-2B2.3B
qwen256K ctxchat
58
tok/s
5% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Apple M3 Pro (36GB).

Find Models for Apple M3 Pro (36GB)Compare with other GPUs