Huozi3.5 needs about 30.2 GB of memory at Q4_K_M (a 28.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 21 quants, from 9.9 GB (IQ1_S) to 38.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Huozi3.5 – 46.9B sparse MoE Llama model with 32K context
Huozi3.5 is a 46.9B parameter sparse mixture‑of‑experts Llama model. It supports 32K context tokens and is available in multiple GGUF quantizations. The model is released under the apache‑2.0 license.
Good at
- Large‑context reasoning
- Mixed‑language support
- Instruction following
Limits
- No vision support
- Requires large VRAM for higher quants
- License is apache‑2.0
Best for
- Chat applications needing long context
- Research on sparse MoE models
- Fine‑tuning with limited VRAM
Who it’s for. Developers and researchers who need a high‑capacity LLM with 32K context and sparse MoE efficiency. The model is suitable for those who can manage the memory requirements of the larger quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 9.9 GB | 11.5 GB | Too big | Get file → | |
| IQ1_M | 11.0 GB | 12.5 GB | Too big | Get file → | |
| IQ2_XXS | 12.7 GB | 14.2 GB | Too big | Get file → | |
| IQ2_XS | 14.0 GB | 15.6 GB | Too big | Get file → | |
| IQ2_S | 14.2 GB | 15.8 GB | Too big | Get file → | |
| IQ2_M | 15.6 GB | 17.2 GB | Too big | Get file → | |
| Q2_K | 17.4 GB | 19.0 GB | Too big | Get file → | |
| IQ3_XXS | 18.4 GB | 19.9 GB | Too big | Get file → | |
| IQ3_XS | 19.5 GB | 21.1 GB | Too big | Get file → | |
| IQ3_S | 20.6 GB | 22.1 GB | Too big | Get file → | |
| Q3_K_S | 20.6 GB | 22.1 GB | Too big | Get file → | |
| IQ3_M | 21.6 GB | 23.1 GB | Too big | Get file → | |
| Q3_K_M | 22.7 GB | 24.2 GB | Too big | Get file → | |
| Q3_K_L | 24.3 GB | 25.9 GB | Too big | Get file → | |
| IQ4_XS | 25.2 GB | 26.8 GB | Too big | Get file → | |
| Q4_0 | 26.7 GB | 28.3 GB | Too big | Get file → | |
| Q4_K_S | 26.9 GB | 28.5 GB | Too big | Get file → | |
| Q4_K_M | 28.6 GB | 30.2 GB | Too big | Get file → | |
| Q5_K_S | 32.4 GB | 34.0 GB | Too big | Get file → | |
| Q5_K_M | 33.4 GB | 35.0 GB | Too big | Get file → | |
| Q6_K | 38.5 GB | 40.1 GB | Too big | Get file → |
For 8‑GB VRAM use IQ1_S (9.93 GB file, 11.5 GB memory at 8K context). For 12‑GB VRAM use IQ1_M (10.95 GB file, 12.5 GB memory). For 24‑GB VRAM use Q4_K_M (28.59 GB file, 30.2 GB memory).
What GPU do you need for Huozi3.5?
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 IQ1_S (9.9 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_S (14.2 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_M (21.6 GB file, about 23.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (28.6 GB file, about 30.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (38.5 GB file, about 40.1 GB in use).
Which Huozi3.5 quant should you choose?
Q4_K_M is the usual starting point for Huozi3.5: it balances file size and quality well. Here it is a 28.6 GB file.
If memory is tight, the smallest file is IQ1_S at 9.9 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 Huozi3.5
How much VRAM does Huozi3.5 need?
About 30.2 GB at Q4_K_M with an 8K context window. That is the 28.6 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 Huozi3.5 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Huozi3.5 GGUF?
It depends on the quant: IQ1_S is 9.9 GB, IQ1_M is 11.0 GB, IQ2_XXS is 12.7 GB, IQ2_XS is 14.0 GB, IQ2_S is 14.2 GB, IQ2_M is 15.6 GB and 15 more.
What context length does Huozi3.5 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Huozi3.5 GGUF?
The files are on Hugging Face in the mradermacher/huozi3.5-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 Huozi3.5 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 Huozi3.5 on 8 GB VRAM?
Use the IQ1_S quantization; it requires about 11.5 GB memory at 8K context, which is close to 8 GB but may need swapping.
Does Huozi3.5 support vision tasks?
No, the model has no vision capabilities.
What license applies to Huozi3.5?
The model is released under the apache‑2.0 license.