- input
- $0.00
- output
- $0.00
- Context
- 262Ktokens
- Released
- 2mo ago
- Size
- 36Bparameters
Cost/1M tokens
Open-weight 35B MoE model for long-horizon research, forecasting, and tool-assisted work
- Language model
- Open weights · 36B
- Reasoning
- Tools
How it compares
Family tree
Models trained from one another, as their makers describe it.
Qwen3.5-35B-A3BQwen · 2026
Additional source evidence
- Source model
- apodex/apodex-1.1-mini
- Last updated
- 2026-08-24
- Model context
- 262K
- Model output limit
- 262K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Temperature control
- Yes
Downloadable weights
Complete source record (JSON)
{
"id": "apodex/apodex-1.1-mini",
"name": "Apodex 1.1 Mini",
"description": "Open-weight 35B MoE model for long-horizon research, forecasting, and tool-assisted work",
"last_updated": "2026-08-24",
"attachment": false,
"reasoning": true,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"release_date": "2026-08-24",
"open_weights": true,
"license": "Apache-2.0",
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/apodex/Apodex-1.1-mini"
}
]
}Frequently asked questions
Running locally
Apodex 1.1 Mini needs an estimated 25.6 GB at Q4, 44.4 GB at Q8 and 83.2 GB at FP16. These figures come from the 36B parameter count and include weights plus about 15% and 0.5 GB for a short context.
No. On a 24 GB, 16 GB, 12 GB or 8 GB GPU it does not fit at Q4, Q8 or FP16 (estimate).
Yes, on a Mac with at least 36 GB of unified memory. Estimated VRAM at Q4 is 25.6 GB, and assuming macOS lets the GPU use about 75% of unified memory, 36 GB is the smallest common Mac memory size that fits (estimate).
Privacy and data
Yes. Apodex 1.1 Mini has open weights, so you can self-host it for full control of your data.
Capabilities and specs
The context window is 262K tokens (262,144) and the maximum output is 236K tokens (235,929).
No. The only input modality is text, so Apodex 1.1 Mini cannot read images, audio, video or PDFs.
Yes, tool calling (function calling) is supported.
Yes, structured output (JSON schema or JSON mode) is supported.
Yes, a reasoning or thinking mode is supported, but reasoning is not always on.
Quality and benchmarks
Qwen3.8 Flash Next by Alibaba, Ornith 1.5 35B A3B by DeepReinforce and Macaron V1 Tall by Mind Lab. They were matched on model kind and release date, with no comparable price.
Qwen3.8 Flash NextApodex 1.1 Mini vs Qwen3.8 Flash NextOrnith 1.5 35B A3BApodex 1.1 Mini vs Ornith 1.5 35B A3BMacaron V1 TallApodex 1.1 Mini vs Macaron V1 Tall
Versions and lineage
Apodex 1.1 Mini is fine-tuned from Qwen3.5-35B-A3B.
Licensing and access
Apodex 1.1 Mini has open weights, licensed under Apache-2.0.
Yes. The Apache 2.0 license is a permissive license that allows commercial use.
The weights are available in the Hugging Face repository apodex/Apodex-1.1-mini.
Basics
Apodex made Apodex 1.1 Mini, and it was released on August 24, 2026.
Apodex 1.1 Mini is an open weights model.
Generated from Vertical Tabs data, updated November 12, 2026.
Discussion
No comments yet
Be the first to share your thoughts.