GRM 3.2 Sky needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.2 GB to 28.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
GRM 3.2 Sky – a large, long‑horizon reasoning model
GRM 3.2 Sky is a 34.7 billion‑parameter model built for long‑horizon agentic tasks and hard reasoning problems. It is optimized for sustained coherence over extended interactions and complex coding, math, and logic workflows.
Good at
- Long‑horizon agentic planning
- Hard coding and debugging
- Advanced mathematics and logic
Limits
- Requires large VRAM for high‑quality quants
- No vision support in the provided GGUFs
- License is apache‑2.0
Best for
- Complex multi‑step coding projects
- Extended reasoning sessions
- Tool‑using agentic workflows
Who it’s for. Developers and researchers needing a model that maintains goal fidelity over many steps. It is suitable for users who can allocate sufficient GPU memory for the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 7.5 GB | 8.7 GB | Too big | Get file → | |
| IQ1_M | 8.2 GB | 9.4 GB | Too big | Get file → | |
| IQ2_XXS | 9.5 GB | 10.7 GB | Too big | Get file → | |
| IQ2_XS | 10.5 GB | 11.7 GB | Too big | Get file → | |
| IQ2_S | 10.7 GB | 11.8 GB | Too big | Get file → | |
| IQ2_M | 11.7 GB | 12.8 GB | Too big | Get file → | |
| Q2_K_S | 12.2 GB | 13.3 GB | Too big | Get file → | |
| Q2_K | 12.9 GB | 14.1 GB | Too big | Get file → | |
| IQ3_XXS | 13.6 GB | 14.8 GB | Too big | Get file → | |
| IQ3_XS | 14.5 GB | 15.7 GB | Too big | Get file → | |
| Q3_K_S | 15.2 GB | 16.4 GB | Too big | Get file → | |
| IQ3_S | 15.3 GB | 16.4 GB | Too big | Get file → | |
| IQ3_M | 15.4 GB | 16.6 GB | Too big | Get file → | |
| Q3_K_M | 16.8 GB | 17.9 GB | Too big | Get file → | |
| Q3_K_L | 18.1 GB | 19.3 GB | Too big | Get file → | |
| IQ4_XS | 18.7 GB | 19.9 GB | Too big | Get file → | |
| Q4_0 | 19.8 GB | 21.0 GB | Too big | Get file → | |
| Q4_K_S | 19.9 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q4_1 | 21.8 GB | 23.0 GB | Too big | Get file → | |
| Q5_K_S | 24.0 GB | 25.2 GB | Too big | Get file → | |
| Q5_K_M | 24.7 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 28.5 GB | 29.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (7.48 GB, 8.7 GB memory at 8K context). For 12 GB VRAM, use IQ2_S (10.65 GB, 11.8 GB memory). For 24 GB VRAM, use Q5_K_M (24.73 GB, 25.9 GB 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 (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 (0.2 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_S (10.7 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XS (14.5 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (21.8 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
Which GRM 3.2 Sky quant should you choose?
Q4_K_M is the usual starting point for GRM 3.2 Sky: it balances file size and quality well. Here it is a 21.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.2 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 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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?
Yes, with the smaller files: the 0.2 GB file needs about 1.4 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 GGUF?
It depends on the quant: file is 0.2 GB, IQ1_S is 7.5 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.5 GB, IQ2_XS is 10.5 GB, IQ2_S is 10.7 GB and 18 more.
What context length does GRM 3.2 Sky 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 GRM 3.2 Sky GGUF?
The files are on Hugging Face in the mradermacher/GRM-3.2-Sky-i1-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 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?
Use the IQ1_S quant, which is 7.48 GB and requires about 8.7 GB memory at 8K context.
Does this model support vision?
The provided GGUF files do not include vision support; it is a text‑only model.
What license applies to this model?
The model is released under the apache‑2.0 license.