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 11 quants, from 12.9 GB (Q2_K) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
GRM 3.2 Sky – a 34.7B‑parameter Qwen‑35MOE model for long‑horizon reasoning
GRM 3.2 Sky is a 34.7B‑parameter Qwen‑35MOE model designed for long‑horizon agentic tasks and difficult reasoning. It supports vision and is optimized for sustained coherence over extended interactions.
Good at
- Long‑horizon agentic workflows
- Hard coding, math, and logic problems
- Robust multi‑file coding
Limits
- Requires large VRAM for higher‑quality quants
- Supports only 8k context in the provided GGUFs
- License is Apache‑2.0
Best for
- Complex multi‑step coding sessions
- Extended planning and tool use
- Advanced mathematical reasoning
Who it’s for. Developers and researchers needing a model that maintains goal fidelity over many steps. The model is suitable for applications that demand reliable long‑horizon reasoning and structured problem solving.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.9 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_S | 15.2 GB | 16.4 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 | 18.9 GB | 20.1 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 → | |
| 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 → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (12.94 GB file, 14.1 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (21.17 GB file, 22.3 GB memory) is a good balance. For 32 GB VRAM, Q6_K (28.51 GB file, 29.7 GB memory) offers higher quality.
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: 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 Q2_K (12.9 GB file, about 14.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 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.
The Q8_0 file is 36.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 12.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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?
Not at an 8K context. The smallest file needs about 14.1 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: Q2_K is 12.9 GB, Q3_K_S is 15.2 GB, Q3_K_M is 16.8 GB, Q3_K_L is 18.1 GB, IQ4_XS is 18.9 GB, Q4_K_S is 19.9 GB and 5 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-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?
No, the smallest quant requires 12.94 GB file size and 14.1 GB memory at 8k context, which exceeds 8 GB VRAM.
Does this model support vision?
Yes, the model has detected vision capabilities.
What license applies to GRM 3.2 Sky?
The model is released under the Apache‑2.0 license.