← Back to Models

hermes-4-70b-mlx

hermes-4-70b-mlx

Publisher
lmstudio-community
Architecture
llama
Parameters
70B
Quantization
4bit (4.0 bpw)
Format
mlx
Max Context
131k tokens
Type
llm
File Size
36.98 GB
Est. RAM
38.5 GB
Est. VRAM
38.5 GB
Capabilities
trained_for_tool_use

Benchmark Results

Compare Models