OrionLLM GRM 3.2 Sky GGUF MTP needs about 21.8 GB of memory at IQ4_NL (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 18.7 GB (IQ4_XS) to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
OrionLLM GRM 3.2 Sky GGUF MTP is a 447M-parameter Grm model in GGUF format, quantized by thread13. Its trained context length is 256K tokens. The repository has 5 quant files, from 18.7 GB (IQ4_XS) to 37.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 18.7 GB | 19.9 GB | Too big | Get file → | |
| IQ4_XS | 19.6 GB | 20.8 GB | Too big | Get file → | |
| IQ4_NL | 20.7 GB | 21.8 GB | Too big | Get file → | |
| Q4_K_S | 20.8 GB | 22.0 GB | Too big | Get file → | |
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → |
What GPU do you need for OrionLLM GRM 3.2 Sky GGUF MTP?
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 Q4_K_S (20.8 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_S (20.8 GB file, about 22.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).
Which OrionLLM GRM 3.2 Sky GGUF MTP quant should you choose?
IQ4_NL (20.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ4_XS at 18.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OrionLLM GRM 3.2 Sky GGUF MTP
How much VRAM does OrionLLM GRM 3.2 Sky GGUF MTP need?
About 21.8 GB at IQ4_NL with an 8K context window. That is the 20.7 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 OrionLLM GRM 3.2 Sky GGUF MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 19.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of OrionLLM GRM 3.2 Sky GGUF MTP GGUF?
It depends on the quant: IQ4_XS is 18.7 GB, IQ4_XS is 19.6 GB, IQ4_NL is 20.7 GB, Q4_K_S is 20.8 GB, Q8_0 is 37.8 GB.
What context length does OrionLLM GRM 3.2 Sky GGUF MTP 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 2.7 GB at 32K.
Where can I download OrionLLM GRM 3.2 Sky GGUF MTP GGUF?
The files are on Hugging Face in the thread13/OrionLLM_GRM-3.2-Sky-GGUF-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 OrionLLM GRM 3.2 Sky GGUF MTP 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.