GRM 3.2 Sky needs about 20.5 GB of memory at its main file (a 17.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 12.7 GB to 26.4 GB.
GRM 3.2 Sky – a 35.5B parameter model for long‑horizon agentic tasks
GRM 3.2 Sky is a 35.5 billion‑parameter model built for long‑horizon agentic workflows and difficult reasoning. It excels at sustained planning, multi‑step coding, and logical problem solving. The model is released under Apache‑2.0 and supports 262,144‑token context.
Good at
- Long‑horizon agentic planning
- Advanced coding and debugging
- Logical reasoning over many steps
Limits
- No vision support
- Requires large VRAM for full context
- License is Apache‑2.0
Best for
- Complex multi‑step coding projects
- Extended planning and tool use
- Hard mathematical and logical reasoning
Who it’s for. Developers and researchers needing a reliable engine for multi‑step workflows and hard reasoning tasks. The model is suitable for users who can allocate sufficient GPU memory for long context lengths.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.7 GB | 14.8 GB | Too big | Get file → | |
| — | 17.9 GB | 20.5 GB | Too big | Get file → | |
| — | 24.0 GB | 27.4 GB | Too big | Get file → | |
| — | 26.4 GB | 30.0 GB | Too big | Get file → |
The available GGUF files are unquantized. The 12.72 GB file needs about 14.8 GB VRAM at 8 k context. The 17.9 GB file needs about 20.5 GB VRAM. For 8 GB VRAM use the 12.72 GB file; for 16 GB VRAM use the 17.9 GB file; for 32 GB VRAM use the 23.99 GB or 26.38 GB files. Memory estimates are approximate.
What GPU do you need for GRM 3.2 Sky?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (12.7 GB file, about 14.8 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (17.9 GB file, about 20.5 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (26.4 GB file, about 30.0 GB in use).
Which GRM 3.2 Sky quant should you choose?
If memory is tight, the smallest file is the first one in the table at 12.7 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GRM 3.2 Sky
How much VRAM does GRM 3.2 Sky need?
About 20.5 GB at its main file with an 8K context window. That is the 17.9 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 GRM 3.2 Sky on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GRM 3.2 Sky GGUF?
It depends on the quant: file is 12.7 GB, file is 17.9 GB, file is 24.0 GB, file is 26.4 GB.
What context length does GRM 3.2 Sky support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download GRM 3.2 Sky GGUF?
The files are on Hugging Face in the thread13/OrionLLM_GRM-3.2-Sky-GGUF-el4-MTP repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does GRM 3.2 Sky 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 GRM 3.2 Sky on 8 GB VRAM?
The smallest file is 12.72 GB and requires about 14.8 GB VRAM at 8 k context, so 8 GB VRAM is insufficient.
Does GRM 3.2 Sky support vision tasks?
No, the model does not include vision capabilities.