NelsaHost
search Login
smart_toy
Mistral Large Language Models

Mixtral 8x22B (141.00B)

Parameters
141.00B
VRAM (FP16)
282.0GB
VRAM (INT4)
70.5GB
Context
65536
check_circle View Compatible GPUs open_in_new View on HuggingFace

tune Quantization Options

Quantization VRAM Required Min GPU
FP16 (Half Precision) 282.0GB A100 / H100
INT8 (8-bit Integer) 141.0GB A100 / H100
Q4_K_M (GGUF 4-bit) 70.5GB A100 / H100
q3_k_m 56.4GB A100 / H100

memory Compatible GPUs

check_circle

H100 SXM

80.0GB VRAM

Perfect
check_circle

H100 SXM

80.0GB VRAM

Perfect
check_circle

H100 PCIe

80.0GB VRAM

Perfect
check_circle

H100 PCIe

80.0GB VRAM

Perfect
check_circle

A100 80GB

80.0GB VRAM

Perfect
check_circle

A100 80GB

80.0GB VRAM

Perfect
View All Compatible GPUs

Model Details

Family Mistral
Category Large Language Models
Parameters 141.00B
Context Length 65536

Similar Models

Mistral 7B 7.00B Mixtral 8x7B 46.70B