Edge0-35B-A3B-preview needs about 20.7 GB of memory at its main file (a 19.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Edge0-35B-A3B-preview – 5.44B parameter text model with MoE
Edge0-35B-A3B-preview is a 5.44B parameter text model using the edge0 architecture and a mixture of experts. It supports reasoning and tool use. The GGUF file is losslessly converted and contains the original tensors.
Good at
- Reasoning
- Tool use
- Large context (262144 tokens)
Limits
- Text generation only
- No vision weights
- Requires rust-model-inference with Edge0 support
Best for
- Complex reasoning tasks
- Tool‑integrated workflows
- Long‑form text generation
Who it’s for. Developers needing a large‑parameter text model with MoE for reasoning tasks. It is suitable for integration into Rust‑based inference pipelines that support the edge0 architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 19.6 GB | 20.7 GB | Too big | Get file → |
The provided GGUF file is unquantized and 19.56 GB in size. It requires approximately 20.7 GB of VRAM at 8 k context. For systems with 20 GB or more VRAM, this file can be loaded directly. No other quantizations are available in the file list.
What GPU do you need for Edge0-35B-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 the main file (19.6 GB file, about 20.7 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Edge0-35B-A3B-preview
How much VRAM does Edge0-35B-A3B-preview need?
About 20.7 GB at its main file with an 8K context window. That is the 19.6 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 Edge0-35B-A3B-preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Edge0-35B-A3B-preview GGUF?
It depends on the quant: file is 19.6 GB.
What context length does Edge0-35B-A3B-preview support?
The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Edge0-35B-A3B-preview GGUF?
The files are on Hugging Face in the EvoAwaken-Workshop/Edge0-35B-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 Edge0-35B-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 this model on 8 GB VRAM?
No, the model requires about 20.7 GB of VRAM at 8 k context.
Can I use this GGUF with llama.cpp?
No, it is only compatible with rust-model-inference Edge0 implementation.
What license does this model use?
Apache‑2.0