Apodex-1.1-mini MLX
MLX conversion of apodex/Apodex-1.1-mini, a 35.95B-parameter Qwen3.5 MoE model for research, data, files, code, and tool-driven work.
This text-only release is optimized for Apple silicon with mlx-lm.
Upstream benchmarks
Results reported by Apodex AI from evaluations of the original Apodex-1.1 model using FrontierAgent, its agent harness and evaluation suite.
Results reported by Apodex AI from evaluations of the original Apodex-1.1-mini checkpoint using FrontierAgent. With the Agent Team workflow, it scored 27.7 on APEX-Agent, 50.2 on FrontierFinance, and 51.7 on FrontierScience-Research.
Release
| Format | Quantization | Size |
|---|---|---|
| MLX safetensors | Affine 4-bit, group size 64 | 19.5 GB |
The MoE router and shared-expert gate weights remain at 8-bit; other eligible weights use affine 4-bit quantization. Image input and native MTP are not included in this MLX release.
Usage
pip install -U mlx-lm
mlx_lm.generate \
--model abenzerps/Apodex-1.1-mini-MLX \
--prompt "Explain why reproducible builds matter." \
--max-tokens 512 --temp 0.7
The 19.5 GB weights require additional unified memory for the runtime and KV cache, particularly at long context lengths. To disable thinking, pass --chat-template-config '{"enable_thinking": false}'.
Source
- Model: apodex/Apodex-1.1-mini
- Chat template revision:
62583b4 - License: Apache-2.0
- Checksums: SHA256SUMS