Clover-35B-A3B-Preview needs about 24.2 GB of memory at Q4_K_M (a 23.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 19.6 GB (Q4_0) to 37.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Clover-35B-A3B-Preview: 35B‑parameter MoE model with 128K context
Clover-35B-A3B-Preview is a 35B‑parameter mixture‑of‑experts model with 3B active parameters per token. It supports a 128K context window and block diffusion generation. The model is released under the apache-2.0 license.
Good at
- Reasoning
- Tools integration
- Large context handling
Limits
- No vision support
- Requires significant VRAM for full precision
- Limited to text-only tasks
Best for
- Long‑form content generation
- Complex reasoning workflows
- Context‑heavy dialogue systems
Who it’s for. Developers and researchers needing a large‑scale, text‑only language model with extensive context. The model is suitable for applications that can accommodate its memory demands and benefit from MoE architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 19.6 GB | 20.8 GB | Too big | Get file → | |
| Q4_K_M | 23.0 GB | 24.2 GB | Too big | Get file → | |
| Q8_0 | 37.9 GB | 39.0 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q4_0 quantization (19.59 GB file, 20.8 GB estimated memory). For 12‑GB VRAM, Q4_K_M (23 GB file, 24.2 GB estimated memory) is recommended. For 16‑GB VRAM or higher, Q8_0 (37.86 GB file, 39 GB estimated memory) provides the highest quality.
What GPU do you need for Clover-35B-A3B-Preview?
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 Q4_0 (19.6 GB file, about 20.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (23.0 GB file, about 24.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.9 GB file, about 39.0 GB in use).
Which Clover-35B-A3B-Preview quant should you choose?
Q4_K_M is the usual starting point for Clover-35B-A3B-Preview: it balances file size and quality well. Here it is a 23.0 GB file.
The Q8_0 file is 37.9 GB, about 1.6 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 Q4_0 at 19.6 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Clover-35B-A3B-Preview
How much VRAM does Clover-35B-A3B-Preview need?
About 24.2 GB at Q4_K_M with an 8K context window. That is the 23.0 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 Clover-35B-A3B-Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Clover-35B-A3B-Preview GGUF?
It depends on the quant: Q4_0 is 19.6 GB, Q4_K_M is 23.0 GB, Q8_0 is 37.9 GB.
What context length does Clover-35B-A3B-Preview support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Clover-35B-A3B-Preview GGUF?
The files are on Hugging Face in the Diffuspace/Clover-35B-A3B-Preview-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 Clover-35B-A3B-Preview 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 Clover-35B-A3B-Preview on 8 GB VRAM?
Use the Q4_0 quantization; it requires about 20.8 GB of VRAM at 8k context, which exceeds 8 GB, so it is not feasible.
Does Clover support vision tasks?
No, Clover is a text‑only model with no vision capabilities.
What license applies to Clover-35B-A3B-Preview?
The model is released under the apache-2.0 license.