Apex 2 Base needs about 3.4 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.6 GB (Q2_K) to 7.7 GB (F16).
Apex 2 Base – 3.87B Mixture‑of‑Experts LLM for continued pretraining
Apex 2 Base is a 3.87B parameter Mixture‑of‑Experts model trained on 86.5B tokens. It is a base checkpoint, suitable for continued pretraining and fine‑tuning. The model is released under apache‑2.0 and supports 4,096‑token context.
Good at
- Continued pretraining
- Fine‑tuning
- Code generation
Limits
- No instruction or chat capability
- Requires 4,096‑token context
- No vision support
Best for
- Extending the Apex family
- Research on MoE architectures
- Custom fine‑tuning projects
Who it’s for. Researchers and developers who need a lightweight base for further training or fine‑tuning. The model is ideal for those working with Qwen3‑MoE architectures and requiring a 3.87B parameter foundation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_M | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_L | 2.1 GB | 2.9 GB | Fits | Get file → | |
| IQ4_XS | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_S | 2.3 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_M | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_S | 2.7 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 3.6 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.0 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 4.9 GB | Fits | Get file → | |
| F16 | 7.7 GB | 8.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.41 GB, estimated 3.4 GB memory). For 12 GB VRAM, Q5_K_M (2.78 GB, 3.8 GB memory) or Q6_K (3.18 GB, 4.2 GB memory). For 16 GB VRAM, Q8_0 (4.12 GB, 5.2 GB memory) or F16 (7.75 GB, 8.8 GB memory). Estimates are approximate.
What GPU do you need for Apex 2 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 Q5_K_M (2.8 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.2 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.7 GB file, about 8.8 GB in use).
Which Apex 2 Base quant should you choose?
Q4_K_M is the usual starting point for Apex 2 Base: it balances file size and quality well. Here it is a 2.4 GB file.
The Q8_0 file is 4.1 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 Q2_K at 1.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Apex 2 Base
How much VRAM does Apex 2 Base need?
About 3.4 GB at Q4_K_M with an 8K context window. That is the 2.4 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 Apex 2 Base on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Apex 2 Base GGUF?
It depends on the quant: Q2_K is 1.6 GB, Q3_K_S is 1.8 GB, Q3_K_M is 2.0 GB, Q3_K_L is 2.1 GB, IQ4_XS is 2.2 GB, Q4_K_S is 2.3 GB and 6 more.
What context length does Apex 2 Base support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.3 GB at 4K.
Where can I download Apex 2 Base GGUF?
The files are on Hugging Face in the mradermacher/Apex-2-Base-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 Apex 2 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 Apex 2 Base on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 3.4 GB of VRAM at 8,096‑token context.
Does Apex 2 Base support chat?
No, it is a base model for text continuation only. Use the Apex‑2 chat version for instruction following.
Is the model licensed for commercial use?
Yes, the model is released under the apache‑2.0 license, allowing commercial use.