GRM 3.2 Sky ONYX needs about 12.3 GB of memory at its main file (a 11.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 7 quants, from 2.3 GB to 25.5 GB.
GRM 3.2 Sky ONYX – a 34.7B parameter model for long‑horizon reasoning
GRM 3.2 Sky ONYX is a 34.7B parameter model built for long‑horizon agentic tasks and difficult reasoning. It is a mixture of experts model optimized for sustained coherence, planning, and multi‑step problem solving.
Good at
- Long‑horizon agentic workflows
- Complex coding and debugging
- Advanced mathematics and logic
Limits
- No vision support
- Requires large VRAM for full precision
- License not specified
Best for
- Agentic workflow automation
- Multi‑step coding projects
- Extended reasoning sessions
Who it’s for. Developers and researchers needing a model that maintains coherence over many steps. Suitable for building agents that plan, execute, and self‑correct across long interactions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.3 GB | 2.8 GB | Fits | Get file → | |
| — | 2.3 GB | 2.8 GB | Fits | Get file → | |
| — | 11.3 GB | 11.8 GB | Too big | Get file → | |
| — | 11.8 GB | 12.3 GB | Too big | Get file → | |
| — | 17.0 GB | 17.5 GB | Too big | Get file → | |
| — | 23.1 GB | 23.6 GB | Too big | Get file → | |
| — | 25.5 GB | 26.0 GB | Too big | Get file → |
For 8‑GB VRAM use the 12‑GB ONYX‑mini quant (file size 11.26 GB, memory 11.8 GB). For 12‑GB VRAM use the 16‑GB compact quant (file size 11.83 GB, memory 12.3 GB). For 16‑GB VRAM use the 17‑GB balanced quant (file size 17 GB, memory 17.5 GB).
What GPU do you need for GRM 3.2 Sky ONYX?
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: the best quant that fits is the main file (2.3 GB file, about 2.8 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (2.3 GB file, about 2.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (2.3 GB file, about 2.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (11.3 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (11.8 GB file, about 12.3 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (23.1 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (25.5 GB file, about 26.0 GB in use).
Which GRM 3.2 Sky ONYX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 2.3 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 ONYX
How much VRAM does GRM 3.2 Sky ONYX need?
About 12.3 GB at its main file with an 8K context window. That is the 11.8 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 ONYX on an 8 GB GPU?
Yes, with the smaller files: the 2.3 GB file needs about 2.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GRM 3.2 Sky ONYX GGUF?
It depends on the quant: file is 2.3 GB, file is 2.3 GB, file is 11.3 GB, file is 11.8 GB, file is 17.0 GB, file is 23.1 GB and 1 more.
What context length does GRM 3.2 Sky ONYX support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.0 GB at 8K and 0.0 GB at 2K.
Where can I download GRM 3.2 Sky ONYX GGUF?
The files are on Hugging Face in the el4/GRM-3.2-Sky-ONYX-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run GRM 3.2 Sky ONYX on 8 GB VRAM?
The 12‑GB ONYX‑mini quant requires about 11.8 GB of VRAM at 8k context, so 8 GB VRAM is insufficient.
Does the model support vision tasks?
No, the model has no vision capability.
What is the context length of the model?
The model was trained with a context length of 2048 tokens.