Diffuspace/Clover-35B-A3B-Preview needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 15.2 GB (Q3_K_S) to 36.9 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 diffusion model with 128K context
Clover-35B-A3B-Preview is a 35B‑parameter mixture‑of‑experts diffusion language model. It uses a hybrid Gated DeltaNet / full‑attention backbone and supports a 128K token context window. The model is text‑only and focuses on coding tasks.
Good at
- Large context generation
- Diffusion block decoding
- Coding assistance
Limits
- Requires llama.cpp built from PR #31306
- No vision support
- Large VRAM needed for full precision
Best for
- Long‑form code generation
- Complex prompt handling
- Research prototyping
Who it’s for. Developers and researchers needing a large‑context, diffusion‑based language model. The model is suitable for applications that can accommodate the high VRAM and CPU requirements of a 35B‑parameter MoE architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 15.2 GB | 16.4 GB | Too big | Get file → | |
| Q3_K_M | 16.8 GB | 17.9 GB | Too big | Get file → | |
| IQ4_XS | 18.9 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q6_K | 28.5 GB | 29.7 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → |
For 8‑GB VRAM, use Q3_K_S (15.19 GB, 16.4 GB memory at 8K context). For 16‑GB VRAM, Q3_K_M (16.77 GB, 17.9 GB memory) or IQ4_XS (18.94 GB, 20.1 GB memory). For 32‑GB VRAM, Q4_K_M (21.17 GB, 22.3 GB memory) or Q6_K (28.52 GB, 29.7 GB memory).
What GPU do you need for Diffuspace/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_K_M (21.2 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which Diffuspace/Clover-35B-A3B-Preview quant should you choose?
Q4_K_M is the usual starting point for Diffuspace/Clover-35B-A3B-Preview: it balances file size and quality well. Here it is a 21.2 GB file.
The Q8_0 file is 36.9 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 Q3_K_S at 15.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Diffuspace/Clover-35B-A3B-Preview
How much VRAM does Diffuspace/Clover-35B-A3B-Preview need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 Diffuspace/Clover-35B-A3B-Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Diffuspace/Clover-35B-A3B-Preview GGUF?
It depends on the quant: Q3_K_S is 15.2 GB, Q3_K_M is 16.8 GB, IQ4_XS is 18.9 GB, Q4_K_M is 21.2 GB, Q6_K is 28.5 GB, Q8_0 is 36.9 GB.
What context length does Diffuspace/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 Diffuspace/Clover-35B-A3B-Preview GGUF?
The files are on Hugging Face in the maternion/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 Diffuspace/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?
The smallest quant, Q3_K_S, requires 15.19 GB file size and estimates 16.4 GB memory at 8K context, so 8 GB VRAM is insufficient.
Does Clover support vision tasks?
No, Clover is a text‑only model and does not support vision.
What license does Clover-35B-A3B-Preview use?
It is released under the Apache-2.0 license.