Austral GLM4 Winton needs about 20.7 GB of memory at Q4_K_M (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 23 quants, from 7.3 GB (IQ1_S) to 26.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.
32.6B parameter GLM4 model with 32768 token context
Austral GLM4 Winton is a 32.6B parameter model based on Delta-Vector/Austral-32B-GLM4-Winton. It supports reasoning and roleplay. The model is released under the Apache‑2.0 license and is available in multiple GGUF quantizations.
Good at
- Reasoning
- Roleplay
- Large context 32768 tokens
Limits
- No vision support
- Requires 8‑k context for memory estimates
- Apache‑2.0 license
Best for
- Chatbot development
- Complex reasoning tasks
- Roleplay scenarios
Who it’s for. Developers and researchers who need a large‑scale GLM4 model with extensive context. The model is suitable for applications that require deep reasoning or role‑play interactions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 7.3 GB | 8.3 GB | Too big | Get file → | |
| IQ1_M | 7.9 GB | 8.9 GB | Too big | Get file → | |
| IQ2_XXS | 9.0 GB | 10.0 GB | Too big | Get file → | |
| IQ2_XS | 9.9 GB | 10.9 GB | Too big | Get file → | |
| IQ2_S | 10.4 GB | 11.4 GB | Too big | Get file → | |
| IQ2_M | 11.3 GB | 12.3 GB | Too big | Get file → | |
| Q2_K_S | 11.4 GB | 12.4 GB | Too big | Get file → | |
| Q2_K | 12.3 GB | 13.3 GB | Too big | Get file → | |
| IQ3_XXS | 12.8 GB | 13.8 GB | Too big | Get file → | |
| IQ3_XS | 13.7 GB | 14.7 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 15.4 GB | Too big | Get file → | |
| IQ3_S | 14.4 GB | 15.4 GB | Too big | Get file → | |
| IQ3_M | 14.8 GB | 15.8 GB | Too big | Get file → | |
| Q3_K_M | 15.9 GB | 16.9 GB | Too big | Get file → | |
| Q3_K_L | 17.2 GB | 18.2 GB | Too big | Get file → | |
| IQ4_XS | 17.6 GB | 18.6 GB | Too big | Get file → | |
| Q4_0 | 18.6 GB | 19.6 GB | Too big | Get file → | |
| Q4_K_S | 18.7 GB | 19.7 GB | Too big | Get file → | |
| Q4_K_M | 19.7 GB | 20.7 GB | Too big | Get file → | |
| Q4_1 | 20.5 GB | 21.6 GB | Too big | Get file → | |
| Q5_K_S | 22.5 GB | 23.5 GB | Too big | Get file → | |
| Q5_K_M | 23.1 GB | 24.1 GB | Too big | Get file → | |
| Q6_K | 26.7 GB | 27.7 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (7.27 GB file, 8.3 GB memory). For 12‑GB VRAM, IQ2_M (11.27 GB file, 12.3 GB memory) or Q2_K (12.29 GB file, 13.3 GB memory). For 20‑GB VRAM, Q4_K_M (19.68 GB file, 20.7 GB memory) or Q5_K_M (23.1 GB file, 24.1 GB memory).
What GPU do you need for Austral GLM4 Winton?
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: the best quant that fits is IQ2_S (10.4 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (14.8 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_S (22.5 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 27.7 GB in use).
Which Austral GLM4 Winton quant should you choose?
Q4_K_M is the usual starting point for Austral GLM4 Winton: it balances file size and quality well. Here it is a 19.7 GB file.
If memory is tight, the smallest file is IQ1_S at 7.3 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 Austral GLM4 Winton
How much VRAM does Austral GLM4 Winton need?
About 20.7 GB at Q4_K_M with an 8K context window. That is the 19.7 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 Austral GLM4 Winton on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Austral GLM4 Winton GGUF?
It depends on the quant: IQ1_S is 7.3 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 9.9 GB, IQ2_S is 10.4 GB, IQ2_M is 11.3 GB and 17 more.
What context length does Austral GLM4 Winton support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.0 GB at 32K.
Where can I download Austral GLM4 Winton GGUF?
The files are on Hugging Face in the mradermacher/Austral-GLM4-Winton-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 Austral GLM4 Winton 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 this model on 8 GB VRAM?
Yes, using the IQ1_S quantization which requires 8.3 GB of VRAM at 8‑k context.
Does this model support vision?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.