FitMyLLM
APPLE/ M3 Ultra

Apple M3 Ultra (192GB)

192 GB
VRAM (Flagship)
800 GB/s
Memory Bandwidth
278 / 290
Models fit at Q4 (96%)
~102 tok/s
7B Q4 speed (Blazing)
Model coverage at Q496% of all models

Specifications

VRAM
192 GB
Bandwidth
800 GB/s
FP16 Compute
28.4 TFLOPS
TDP
215W
Memory
LPDDR5
Architecture
M3 Ultra
MSRP
$6,999
214
Fast models (>30 tok/s)
Real-time chat speed
267
Usable models (>10 tok/s)
Comfortable for all tasks
278
Total compatible
Fit in VRAM at Q4

Compatible Models(278)

S
GPT-2 124M0.124B
gpt21K ctxchat
5735
tok/s
0% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
5267
tok/s
0% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
5191
tok/s
0% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
2123
tok/s
0% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
2123
tok/s
0% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
2061
tok/s
0% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
1975
tok/s
0% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
1422
tok/s
0% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
1422
tok/s
0% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
1252
tok/s
0% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
1185
tok/s
0% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
919
tok/s
0% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
889
tok/s
0% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
790
tok/s
1% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
711
tok/s
1% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
711
tok/s
1% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
646
tok/s
1% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
646
tok/s
1% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
593
tok/s
1% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
593
tok/s
0% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
547
tok/s
1% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
547
tok/s
1% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
547
tok/s
1% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
547
tok/s
1% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
474
tok/s
1% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
474
tok/s
1% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
474
tok/s
1% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
474
tok/s
1% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
474
tok/s
1% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
444
tok/s
1% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
418
tok/s
1% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
416
tok/s
1% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
395
tok/s
1% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
374
tok/s
1% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
356
tok/s
2% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
356
tok/s
1% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
356
tok/s
1% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
356
tok/s
1% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
322
tok/s
1% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
309
tok/s
1% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Apple M3 Ultra (192GB).

Find Models for Apple M3 Ultra (192GB)Compare with other GPUs