Drex v2.0 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 11 quants, from 12.9 GB (Q2_K) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Drex v2.0 – a decision model with vision support
Drex v2.0 is a decision model built on Qwen3.6-35B-A3B, a mixture of experts with 35B parameters and about 3B active per token. It answers typed questions about a given context without generating text. The model supports vision but the vision tower is dropped on load.
Good at
- Decision tasks
- Email classification
- Game arena performance
Limits
- No text generation
- Vision tower not loaded
- License is other
Best for
- Decision support systems
- Email filtering
- Game AI evaluation
Who it’s for. Developers needing a lightweight decision model that can run locally with Python, llama.cpp or Ollama. The model is suitable for applications that require probability outputs for multiple-choice questions without generating text.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.9 GB | 14.1 GB | Too big | Get file → | |
| 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 → | |
| Q3_K_L | 18.1 GB | 19.3 GB | Too big | Get file → | |
| IQ4_XS | 18.9 GB | 20.1 GB | Too big | Get file → | |
| Q4_K_S | 19.9 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q5_K_S | 24.0 GB | 25.2 GB | Too big | Get file → | |
| Q5_K_M | 24.7 GB | 25.9 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 Q2_K (12.94 GB file, 14.1 GB memory at 8 k context). For 16 GB VRAM use Q4_K_M (21.17 GB file, 22.3 GB memory). For 32 GB VRAM use Q6_K (28.51 GB file, 29.7 GB memory).
What GPU do you need for Drex v2.0?
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: the best quant that fits is Q2_K (12.9 GB file, about 14.1 GB in use).
- 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 Drex v2.0 quant should you choose?
Q4_K_M is the usual starting point for Drex v2.0: 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 Q2_K at 12.9 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 Drex v2.0
How much VRAM does Drex v2.0 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 Drex v2.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Drex v2.0 GGUF?
It depends on the quant: Q2_K is 12.9 GB, Q3_K_S is 15.2 GB, Q3_K_M is 16.8 GB, Q3_K_L is 18.1 GB, IQ4_XS is 18.9 GB, Q4_K_S is 19.9 GB and 5 more.
What context length does Drex v2.0 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 Drex v2.0 GGUF?
The files are on Hugging Face in the mradermacher/drex-v2.0-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 Drex v2.0 use?
Hugging Face lists the license as other. 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 Drex v2.0 on 8 GB VRAM?
Yes, the Q2_K quant file is 12.94 GB and requires about 14.1 GB memory at 8 k context, which fits within 8 GB VRAM with off‑load or swapping.
Does the model generate text?
No, Drex v2.0 only scores questions and returns probabilities; no text generation occurs.
Is the vision tower usable?
The vision tower is dropped on load, so vision functionality is not available in the current GGUF files.