GroveMoE Base needs about 21.5 GB of memory at Q4_K_M (a 20.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.2 GB to 27.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
GroveMoE Base – a 33 B sparse LLM with dynamic expert activation
GroveMoE Base is a 33 B parameter model built on a sparse architecture that activates only 3.14–3.28 B parameters per token. It uses adjugate experts for efficient computation and supports a 32 768 token context window. The model is released under the Apache‑2.0 license.
Good at
- Sparse expert inference
- Large context handling
- Dynamic compute allocation
Limits
- No vision support
- Requires 8 k context for memory estimates
- License is Apache‑2.0
Best for
- Research on sparse models
- Low‑latency inference on GPUs
- Fine‑tuning with limited VRAM
Who it’s for. Researchers and developers interested in sparse LLMs who need a large context window and can manage the memory requirements. The model is suitable for those who prefer open‑source licensing and are comfortable with GGUF quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 1.5 GB | Fits | Get file → | |
| IQ1_S | 7.1 GB | 8.4 GB | Too big | Get file → | |
| IQ1_M | 7.8 GB | 9.1 GB | Too big | Get file → | |
| IQ2_XXS | 9.0 GB | 10.3 GB | Too big | Get file → | |
| IQ2_XS | 10.0 GB | 11.3 GB | Too big | Get file → | |
| IQ2_S | 10.1 GB | 11.4 GB | Too big | Get file → | |
| IQ2_M | 11.1 GB | 12.4 GB | Too big | Get file → | |
| Q2_K_S | 11.5 GB | 12.8 GB | Too big | Get file → | |
| Q2_K | 12.2 GB | 13.5 GB | Too big | Get file → | |
| IQ3_XXS | 12.9 GB | 14.2 GB | Too big | Get file → | |
| IQ3_XS | 13.7 GB | 15.0 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 15.7 GB | Too big | Get file → | |
| IQ3_S | 14.4 GB | 15.7 GB | Too big | Get file → | |
| IQ3_M | 14.7 GB | 16.0 GB | Too big | Get file → | |
| Q3_K_M | 16.0 GB | 17.3 GB | Too big | Get file → | |
| Q3_K_L | 17.2 GB | 18.5 GB | Too big | Get file → | |
| IQ4_XS | 17.7 GB | 19.0 GB | Too big | Get file → | |
| Q4_0 | 18.7 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 18.9 GB | 20.2 GB | Too big | Get file → | |
| Q4_K_M | 20.2 GB | 21.5 GB | Too big | Get file → | |
| Q4_1 | 20.7 GB | 22.0 GB | Too big | Get file → | |
| Q5_K_S | 22.8 GB | 24.1 GB | Too big | Get file → | |
| Q5_K_M | 23.6 GB | 24.9 GB | Too big | Get file → | |
| Q6_K | 27.3 GB | 28.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (7.1 GB file, 8.4 GB memory) or IQ1_M (7.82 GB file, 9.1 GB memory). If 12 GB VRAM is available, Q2_K (12.24 GB file, 13.5 GB memory) or Q3_K_S (14.44 GB file, 15.7 GB memory) provide a good balance of size and performance. Larger VRAM allows higher‑quality quants such as Q4_K_M (20.17 GB file, 21.5 GB memory).
What GPU do you need for GroveMoE Base?
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: the best quant that fits is the main file (0.2 GB file, about 1.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.5 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_S (10.1 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (14.7 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (20.7 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (27.3 GB file, about 28.6 GB in use).
Which GroveMoE Base quant should you choose?
Q4_K_M is the usual starting point for GroveMoE Base: it balances file size and quality well. Here it is a 20.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.2 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GroveMoE Base
How much VRAM does GroveMoE Base need?
About 21.5 GB at Q4_K_M with an 8K context window. That is the 20.2 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 GroveMoE Base on an 8 GB GPU?
Yes, with the smaller files: the 0.2 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GroveMoE Base GGUF?
It depends on the quant: file is 0.2 GB, IQ1_S is 7.1 GB, IQ1_M is 7.8 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.1 GB and 18 more.
What context length does GroveMoE Base support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download GroveMoE Base GGUF?
The files are on Hugging Face in the mradermacher/GroveMoE-Base-i1-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 GroveMoE Base 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 GroveMoE Base on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM, though memory usage is approximate.
Does GroveMoE Base support vision tasks?
No, the model has no vision capabilities.