Quen32 needs about 18.0 GB of memory at BF16 (a 15.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 15.6 GB (BF16) to 18.6 GB (Q4_0).
Quen32 – a 33‑billion‑parameter text‑only LLM in GGUF format
Quen32 is a 33‑billion‑parameter model finetuned and converted to GGUF using Unsloth. It is available in BF16 and Q4_0 quantisations. The model is designed for text‑only applications and can be run with llama‑cpp or Ollama.
Good at
- Large‑scale text generation
- Fine‑grained language tasks
- High‑capacity reasoning
Limits
- No vision support
- License not specified
- Requires large VRAM for full precision
Best for
- Chatbots needing deep context
- Content creation with long documents
- Research prototypes requiring large models
Who it’s for. Developers and researchers who need a high‑parameter LLM for text generation and want to deploy it locally using GGUF. The model is suitable for environments that can accommodate its memory demands.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 15.6 GB | 18.0 GB | Too big | Get file → | |
| Q4_0 | 18.6 GB | 21.4 GB | Too big | Get file → |
For 8‑k context, the BF16 file (~15.62 GB) needs about 18 GB of VRAM. The Q4_0 file (~18.64 GB) requires roughly 21.4 GB of VRAM. Choose BF16 if you have at least 18 GB VRAM, otherwise use Q4_0 for a slightly larger memory footprint but lower precision.
What GPU do you need for Quen32?
These figures add the file size, an fp16 KV cache at an 8K context window 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_0 (18.6 GB file, about 21.4 GB in use).
Which Quen32 quant should you choose?
BF16 (15.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Quen32
How much VRAM does Quen32 need?
About 18.0 GB at BF16 with an 8K context window. That is the 15.6 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 Quen32 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Quen32 GGUF?
It depends on the quant: BF16 is 15.6 GB, Q4_0 is 18.6 GB.
Where can I download Quen32 GGUF?
The files are on Hugging Face in the AlSamCur123/Quen32 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Quen32 on 8 GB VRAM?
No. The smallest quantisation requires at least 18 GB of VRAM for 8‑k context.
Does Quen32 support image input?
No, Quen32 is a text‑only model.
Is there an Ollama Modelfile available?
Yes, an Ollama Modelfile is included for easy deployment.