Iris Mini needs about 16.5 GB of memory at its main file (a 15.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Iris Mini APEX-I-MiniPlus V2.1 – a 35.5B MoE search agent with 256K context
Iris Mini is a 35.5B parameter Mixture‑of‑Experts model based on qwen35moe. It is trained as a search agent, capable of reasoning and vision tasks. The GGUF release is unquantized and requires about 16.5GB of RAM/VRAM at 8K context.
Good at
- Reasoning and search loops
- Vision integration
- Long‑context handling
Limits
- Unquantized file size 15.3GB
- Requires ~16.5GB memory at 8K context
- No other quantizations available
Best for
- Search‑driven question answering
- Vision‑augmented data retrieval
- Long‑form reasoning
Who it’s for. Developers building search agents or vision‑enabled assistants who need a large‑context, Mixture‑of‑Experts model. The model is licensed under Apache‑2.0 and can be run with llama.cpp or SGLang.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 15.3 GB | 16.5 GB | Too big | Get file → |
For 16GB VRAM, use the unquantized GGUF file (15.3GB). If a larger VRAM budget is available, no other quantizations are provided, so the same file must be used. Memory estimates are approximate.
What GPU do you need for Iris Mini?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (15.3 GB file, about 16.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Iris Mini
How much VRAM does Iris Mini need?
About 16.5 GB at its main file with an 8K context window. That is the 15.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Iris Mini on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Iris Mini GGUF?
It depends on the quant: file is 15.3 GB.
What context length does Iris Mini support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download Iris Mini GGUF?
The files are on Hugging Face in the IsValorum/Iris-mini-APEX-I-MiniPlus-V2.1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Iris Mini use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Iris Mini on 8 GB VRAM?
No, the model requires about 16.5GB of memory at 8K context, which exceeds 8 GB VRAM.
Does Iris Mini support vision tasks?
Yes, the model has detected vision abilities and can process image inputs.