FitMyLLM
NVIDIA/ Blackwell 2.0

NVIDIA GB10

128 GB
VRAM (Flagship)
273 GB/s
Memory Bandwidth
274 / 290
Models fit at Q4 (94%)
~31 tok/s
7B Q4 speed (Fast)
Model coverage at Q494% of all models

Specifications

VRAM
128 GB
Bandwidth
273 GB/s
FP16 Compute
29.7 TFLOPS
TDP
140W
Memory
LPDDR5X
Architecture
Blackwell 2.0
CUDA Cores
6,144
Tensor Cores
384
PCIe
Gen 5 x16
121
Fast models (>30 tok/s)
Real-time chat speed
208
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
1761
tok/s
0% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
1618
tok/s
0% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
1594
tok/s
0% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
652
tok/s
0% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
652
tok/s
0% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
633
tok/s
0% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
607
tok/s
0% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
437
tok/s
1% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
437
tok/s
1% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
385
tok/s
0% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
364
tok/s
0% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
282
tok/s
1% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
273
tok/s
1% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
243
tok/s
1% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
218
tok/s
1% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
218
tok/s
1% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
199
tok/s
1% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
199
tok/s
1% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
182
tok/s
1% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
182
tok/s
1% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
168
tok/s
1% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
168
tok/s
1% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
168
tok/s
1% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
168
tok/s
1% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
146
tok/s
1% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
146
tok/s
1% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
146
tok/s
1% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
146
tok/s
1% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
146
tok/s
1% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
137
tok/s
1% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
128
tok/s
1% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
128
tok/s
1% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
121
tok/s
1% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
115
tok/s
1% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
109
tok/s
3% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
109
tok/s
1% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
109
tok/s
1% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
109
tok/s
1% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
99
tok/s
1% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
95
tok/s
1% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your GB10.

Find Models for GB10Compare with other GPUs