FitMyLLM
NVIDIA/ Blackwell

NVIDIA B200

90 GB
VRAM (Flagship)
4100 GB/s
Memory Bandwidth
272 / 290
Models fit at Q4 (94%)
~469 tok/s
7B Q4 speed (Blazing)
Model coverage at Q494% of all models

Specifications

VRAM
90 GB
Bandwidth
4100 GB/s
FP16 Compute
1191.2 TFLOPS
TDP
1000W
Memory
HBM3e
Architecture
Blackwell
CUDA Cores
18,944
Tensor Cores
592
PCIe
Gen 5 x16
268
Fast models (>30 tok/s)
Real-time chat speed
272
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
26452
tok/s
0% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
24296
tok/s
0% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
23942
tok/s
0% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
9791
tok/s
0% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
9791
tok/s
0% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
9507
tok/s
1% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
9111
tok/s
1% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
6560
tok/s
1% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
6560
tok/s
1% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
5775
tok/s
1% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
5467
tok/s
1% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
4238
tok/s
1% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
4100
tok/s
1% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
3644
tok/s
1% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
3280
tok/s
1% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
3280
tok/s
1% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
2982
tok/s
1% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
2982
tok/s
1% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
2733
tok/s
1% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
2733
tok/s
1% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
2523
tok/s
1% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
2523
tok/s
1% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
2523
tok/s
1% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
2523
tok/s
1% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
2187
tok/s
1% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
2187
tok/s
1% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
2187
tok/s
1% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
2187
tok/s
1% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
2187
tok/s
1% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
2050
tok/s
2% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
1929
tok/s
2% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
1918
tok/s
2% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
1822
tok/s
2% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
1726
tok/s
2% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
1640
tok/s
5% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
1640
tok/s
2% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
1640
tok/s
2% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
1640
tok/s
2% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
1484
tok/s
2% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
1426
tok/s
2% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your B200.

Find Models for B200Compare with other GPUs