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 14 quants, from 17.4 GB (Q2_K) to 49.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Huozi3.5 – 46.9B sparse mixture of experts Llama model
Huozi3.5 is a 46.9B parameter sparse mixture of experts model based on HIT‑SCIR/huozi3.5. It supports a 32K context window and is trained on Chinese and English data. The model is released under the apache‑2.0 license.
Good at
- Large context reasoning
- Chinese and English language tasks
- Instruction following
Limits
- Sparse MoE requires top‑2 activation
- No vision support
- Requires 8K context for memory estimates
Best for
- Long‑form dialogue
- Code generation
- Multilingual content creation
Who it’s for. Researchers and developers needing a large, context‑rich LLM for Chinese and English tasks. The model is suitable for fine‑tuning and inference on systems with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 17.4 GB | 19.0 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 | 25.5 GB | 27.1 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 → | |
| Q8_0 | 49.8 GB | 51.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 17.43 GB, estimated 19 GB memory at 8K context). For 16 GB VRAM, Q4_K_M (file size 28.59 GB, estimated 30.2 GB memory) or Q5_K_M (file size 33.38 GB, estimated 35 GB). For 24 GB VRAM, Q6_K (file size 38.55 GB, estimated 40.1 GB) offers higher quality. All estimates are approximate.
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: 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 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.
The Q8_0 file is 49.8 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 17.4 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 19.0 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: Q2_K is 17.4 GB, IQ3_XS is 19.5 GB, IQ3_S is 20.6 GB, Q3_K_S is 20.6 GB, IQ3_M is 21.6 GB, Q3_K_M is 22.7 GB and 8 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-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 Q2_K quant, which requires about 19 GB of VRAM at 8K context. 8 GB VRAM is insufficient for any quant.
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.