FitMyLLM
NVIDIA/ Blackwell 2.0

NVIDIA RTX PRO 5000 72 GB Blackwell

72 GB
VRAM (Flagship)
1340 GB/s
Memory Bandwidth
263 / 290
Models fit at Q4 (91%)
~153 tok/s
7B Q4 speed (Blazing)
Model coverage at Q491% of all models

Specifications

VRAM
72 GB
Bandwidth
1340 GB/s
FP16 Compute
66.9 TFLOPS
TDP
300W
Memory
GDDR7
Architecture
Blackwell 2.0
CUDA Cores
14,080
Tensor Cores
440
PCIe
Gen 5 x16
240
Fast models (>30 tok/s)
Real-time chat speed
263
Usable models (>10 tok/s)
Comfortable for all tasks
263
Total compatible
Fit in VRAM at Q4

Compatible Models(263)

S
GPT-2 124M0.124B
gpt21K ctxchat
8645
tok/s
1% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
7941
tok/s
1% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
7825
tok/s
0% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
3200
tok/s
1% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
3200
tok/s
1% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
3107
tok/s
1% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
2978
tok/s
1% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
2144
tok/s
1% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
2144
tok/s
1% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
1887
tok/s
1% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
1787
tok/s
1% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
1385
tok/s
1% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
1340
tok/s
1% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
1191
tok/s
1% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
1072
tok/s
1% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
1072
tok/s
1% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
975
tok/s
2% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
975
tok/s
2% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
893
tok/s
2% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
893
tok/s
1% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
825
tok/s
2% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
825
tok/s
2% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
825
tok/s
2% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
825
tok/s
2% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
715
tok/s
2% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
715
tok/s
2% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
715
tok/s
2% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
715
tok/s
2% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
715
tok/s
2% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
670
tok/s
2% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
631
tok/s
2% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
627
tok/s
2% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
596
tok/s
2% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
564
tok/s
2% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
536
tok/s
6% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
536
tok/s
2% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
536
tok/s
2% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
536
tok/s
2% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
485
tok/s
2% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
466
tok/s
2% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your RTX PRO 5000 72 GB Blackwell.

Find Models for RTX PRO 5000 72 GB BlackwellCompare with other GPUs