FitMyLLM
INTEL/ Generation 12.5

Intel Data Center GPU Max 1350

96 GB
VRAM (Flagship)
2460 GB/s
Memory Bandwidth
272 / 290
Models fit at Q4 (94%)
~112 tok/s
7B Q4 speed (Blazing)
Model coverage at Q494% of all models

Specifications

VRAM
96 GB
Bandwidth
2460 GB/s
FP16 Compute
44.4 TFLOPS
TDP
450W
Memory
HBM2e
Architecture
Generation 12.5
Compute Units
896
PCIe
Gen 5 x16
210
Fast models (>30 tok/s)
Real-time chat speed
263
Usable models (>10 tok/s)
Comfortable for all tasks
272
Total compatible
Fit in VRAM at Q4

Compatible Models(272)

S
GPT-2 124M0.124B
gpt21K ctxchat
6348
tok/s
0% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
5831
tok/s
0% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
5746
tok/s
0% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
2350
tok/s
0% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
2350
tok/s
0% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
2282
tok/s
1% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
2187
tok/s
1% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
1574
tok/s
1% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
1574
tok/s
1% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
1386
tok/s
1% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
1312
tok/s
1% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
1017
tok/s
1% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
984
tok/s
1% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
875
tok/s
1% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
787
tok/s
1% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
787
tok/s
1% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
716
tok/s
1% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
716
tok/s
1% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
656
tok/s
1% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
656
tok/s
1% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
606
tok/s
1% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
606
tok/s
1% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
606
tok/s
1% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
606
tok/s
1% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
525
tok/s
1% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
525
tok/s
1% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
525
tok/s
1% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
525
tok/s
1% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
525
tok/s
1% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
492
tok/s
1% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
463
tok/s
1% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
460
tok/s
1% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
437
tok/s
2% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
414
tok/s
1% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
394
tok/s
5% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
394
tok/s
2% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
394
tok/s
2% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
394
tok/s
2% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
356
tok/s
2% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
342
tok/s
2% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Data Center GPU Max 1350.

Find Models for Data Center GPU Max 1350Compare with other GPUs