FitMyLLM
NVIDIA/ Hopper

NVIDIA H100 SXM5 80 GB

80 GB
VRAM (Flagship)
3360 GB/s
Memory Bandwidth
267 / 290
Models fit at Q4 (92%)
~384 tok/s
7B Q4 speed (Blazing)
Model coverage at Q492% of all models

Specifications

VRAM
80 GB
Bandwidth
3360 GB/s
FP16 Compute
267.6 TFLOPS
TDP
700W
Memory
HBM3
Architecture
Hopper
CUDA Cores
16,896
Tensor Cores
528
PCIe
Gen 5 x16
262
Fast models (>30 tok/s)
Real-time chat speed
267
Usable models (>10 tok/s)
Comfortable for all tasks
267
Total compatible
Fit in VRAM at Q4

Compatible Models(267)

S
GPT-2 124M0.124B
gpt21K ctxchat
21677
tok/s
0% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
19911
tok/s
0% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
19620
tok/s
0% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
8024
tok/s
1% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
8024
tok/s
1% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
7791
tok/s
1% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
7467
tok/s
1% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
5376
tok/s
1% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
5376
tok/s
1% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
4732
tok/s
1% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
4480
tok/s
1% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
3473
tok/s
1% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
3360
tok/s
1% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
2987
tok/s
1% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
2688
tok/s
1% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
2688
tok/s
1% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
2444
tok/s
1% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
2444
tok/s
1% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
2240
tok/s
1% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
2240
tok/s
1% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
2068
tok/s
2% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
2068
tok/s
1% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
2068
tok/s
2% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
2068
tok/s
2% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
1792
tok/s
2% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
1792
tok/s
2% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
1792
tok/s
2% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
1792
tok/s
2% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
1792
tok/s
2% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
1680
tok/s
2% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
1581
tok/s
2% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
1572
tok/s
2% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
1493
tok/s
2% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
1415
tok/s
2% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
1344
tok/s
6% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
1344
tok/s
2% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
1344
tok/s
2% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
1344
tok/s
2% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
1216
tok/s
2% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
1169
tok/s
2% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your H100 SXM5 80 GB.

Find Models for H100 SXM5 80 GBCompare with other GPUs