This repository contains an MLX-LM conversion of InternScience/Agents-A1. Conversion Details Original model: InternScience/Agents-A1 Model family: Agents A1 Source model type: qwen3 5 moe Model size: 35,107,181,936 parameters Quantization: MLX-LM affine quantization Bits: 4-bit Group size: 64 Local MLX folder size at upload time: 18.19 GiB Local safetensors weight size at upload time: 18.17 GiB...
--- library_name: mlx base_model: InternScience/Agents-A1 license: apache-2.0 pipeline_tag: text-generation tags: - mlx - mlx-lm - quantized - 4-bit - base_model:InternScience/Agents-A1 --- # Agents-A1 MLX 4-bit This repository contains an MLX-LM conversion of [InternScience/Agents-A1](https://huggingface.co/InternScience/Agents-A1). ## Conversion Details - Original model: `InternScience/Agents-A1` - Model family: Agents A1 - Source model type: `qwen3_5_moe` - Model size: 35,107,181,936 parameters - Quantization: MLX-LM affine quantization - Bits: 4-bit - Group size: 64 - Local MLX folder size at upload time: 18.19 GiB - Local safetensors weight size at upload time: 18.17 GiB ## Usage ```bash mlx_lm.generate --model DreamFoundries/Agents-A1-4bit --prompt "Hello" --max-tokens 64 ``` ## Benchmarks No comparative benchmarks have been run yet. The repository does not currently provide quality, speed, memory, or benchmark comparisons against the original weights or other quantizations. ## License This is a converted/quantized derivative of the original model. Please refer to the original model repository for the upstream license and usage terms: https://huggingface.co/InternScience/Agents-A1
This repository contains an MLX-LM conversion of InternScience/Agents-A1. Conversion Details Original model: InternScience/Agents-A1 Model family: Agents A1 Source model type: qwen3 5 moe Model size: 35,107,181,936 parameters Quantization: MLX-LM affine…
