Clover 35B A3B Preview BF16 needs about 70.6 GB of memory at BF16 (a 69.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Clover 35B A3B Preview BF16 – 35B parameter MoE model with 128K context
Clover 35B A3B Preview BF16 is a 34.7B‑parameter mixture‑of‑experts model with 3B active parameters per token. It supports 131072 context tokens and is optimized for block diffusion generation. The model is released under Apache‑2.0.
Good at
- Reasoning
- Tool usage
- Long‑form context
Limits
- Requires clover_moe runtime
- Large VRAM (~70.6 GB at 8k context)
- No vision support
Best for
- Complex reasoning tasks
- Tool‑integrated workflows
- Extended dialogue
Who it’s for. Developers and researchers needing a large‑context, MoE language model for text‑only applications. The model is suitable for environments where the custom clover_moe runtime is available.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 69.4 GB | 70.6 GB | Too big | Get file → |
The only available quant is BF16, file size 69.38 GB. It requires approximately 70.6 GB VRAM at 8k context. For lower memory budgets, no other quant is provided.
What GPU do you need for Clover 35B A3B Preview BF16?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Clover 35B A3B Preview BF16 quant should you choose?
BF16 (69.4 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 Clover 35B A3B Preview BF16
How much VRAM does Clover 35B A3B Preview BF16 need?
About 70.6 GB at BF16 with an 8K context window. That is the 69.4 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 BF16 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 70.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Clover 35B A3B Preview BF16 GGUF?
It depends on the quant: BF16 is 69.4 GB.
What context length does Clover 35B A3B Preview BF16 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 BF16 GGUF?
The files are on Hugging Face in the IsValorum/Clover-35B-A3B-Preview-BF16-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 BF16 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 BF16 on 8 GB VRAM?
No. The BF16 quant requires about 70.6 GB VRAM at 8k context, far exceeding 8 GB.
Does Clover support vision tasks?
No. Clover is a text‑only model with no vision capabilities.
What runtime is needed for this model?
Use the precompiled clover_moe runtimes from IsValorum/llama.cpp-clover-moe or compile from the patched branch.