FitMyLLM
APPLE/ M4 Pro

Apple M4 Pro (48GB)

48 GB
VRAM (Flagship)
273 GB/s
Memory Bandwidth
253 / 290
Models fit at Q4 (87%)
~35 tok/s
7B Q4 speed (Fast)
Model coverage at Q487% of all models

Specifications

VRAM
48 GB
Bandwidth
273 GB/s
FP16 Compute
9.2 TFLOPS
TDP
30W
Memory
Unified
Architecture
M4 Pro
MSRP
$1,799
143
Fast models (>30 tok/s)
Real-time chat speed
203
Usable models (>10 tok/s)
Comfortable for all tasks
253
Total compatible
Fit in VRAM at Q4

Compatible Models(253)

S
GPT-2 124M0.124B
gpt21K ctxchat
1957
tok/s
1% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
1798
tok/s
1% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
1771
tok/s
1% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
724
tok/s
1% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
724
tok/s
1% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
703
tok/s
1% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
674
tok/s
1% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
485
tok/s
2% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
485
tok/s
2% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
427
tok/s
1% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
404
tok/s
1% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
314
tok/s
2% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
303
tok/s
2% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
270
tok/s
2% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
243
tok/s
2% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
243
tok/s
2% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
221
tok/s
2% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
221
tok/s
2% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
202
tok/s
2% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
202
tok/s
1% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
187
tok/s
3% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
187
tok/s
2% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
187
tok/s
3% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
187
tok/s
3% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
162
tok/s
3% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
162
tok/s
3% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
162
tok/s
3% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
162
tok/s
3% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
162
tok/s
3% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
152
tok/s
3% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
143
tok/s
3% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
142
tok/s
3% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
135
tok/s
3% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
128
tok/s
3% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
121
tok/s
9% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
121
tok/s
3% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
121
tok/s
3% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
121
tok/s
3% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
110
tok/s
4% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
106
tok/s
4% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Apple M4 Pro (48GB).

Find Models for Apple M4 Pro (48GB)Compare with other GPUs