NelsaHost
search Login
smart_toy
Mistral Large Language Models

Mistral 7B (7.00B)

Parameters
7.00B
VRAM (FP16)
14.0GB
VRAM (INT4)
3.5GB
Context
32768
check_circle View Compatible GPUs open_in_new View on HuggingFace

tune Quantization Options

Quantization VRAM Required Min GPU
FP16 (Half Precision) 14.0GB RTX 4080
INT8 (8-bit Integer) 7.0GB RTX 3070 / 4060
Q4_K_M (GGUF 4-bit) 3.5GB RTX 3070 / 4060
q3_k_m 2.8GB RTX 3070 / 4060

memory Compatible GPUs

check_circle

RTX 4090

24.0GB VRAM

Perfect
check_circle

RTX 4090

24.0GB VRAM

Perfect
check_circle

RTX 4090

24.0GB VRAM

Perfect
check_circle

RTX 4090

24.0GB VRAM

Perfect
check_circle

RTX 3090 Ti

24.0GB VRAM

Perfect
check_circle

RTX 3090 Ti

24.0GB VRAM

Perfect
View All Compatible GPUs

Model Details

Family Mistral
Category Large Language Models
Parameters 7.00B
Context Length 32768

Similar Models

Mixtral 8x22B 141.00B Mixtral 8x7B 46.70B