FitMyLLM
INTEL/ Generation 12.5

Intel Data Center GPU Max Subsystem

128 GB
VRAM (Flagship)
3210 GB/s
Memory Bandwidth
274 / 290
Models fit at Q4 (94%)
~147 tok/s
7B Q4 speed (Blazing)
Model coverage at Q494% of all models

Specifications

VRAM
128 GB
Bandwidth
3210 GB/s
FP16 Compute
52.4 TFLOPS
TDP
2400W
Memory
HBM2e
Architecture
Generation 12.5
Compute Units
1024
PCIe
Gen 5 x16
241
Fast models (>30 tok/s)
Real-time chat speed
266
Usable models (>10 tok/s)
Comfortable for all tasks
274
Total compatible
Fit in VRAM at Q4

Compatible Models(274)

S
GPT-2 124M0.124B
gpt21K ctxchat
8284
tok/s
0% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
7609
tok/s
0% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
7498
tok/s
0% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
3066
tok/s
0% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
3066
tok/s
0% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
2977
tok/s
0% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
2853
tok/s
0% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
2054
tok/s
1% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
2054
tok/s
1% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
1808
tok/s
0% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
1712
tok/s
0% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
1327
tok/s
1% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
1284
tok/s
1% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
1141
tok/s
1% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
1027
tok/s
1% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
1027
tok/s
1% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
934
tok/s
1% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
934
tok/s
1% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
856
tok/s
1% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
856
tok/s
1% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
790
tok/s
1% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
790
tok/s
1% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
790
tok/s
1% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
790
tok/s
1% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
685
tok/s
1% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
685
tok/s
1% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
685
tok/s
1% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
685
tok/s
1% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
685
tok/s
1% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
642
tok/s
1% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
604
tok/s
1% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
601
tok/s
1% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
571
tok/s
1% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
541
tok/s
1% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
514
tok/s
3% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
514
tok/s
1% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
514
tok/s
1% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
514
tok/s
1% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
465
tok/s
1% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
447
tok/s
1% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Data Center GPU Max Subsystem.

Find Models for Data Center GPU Max SubsystemCompare with other GPUs