drex v2.0 Q8 0 needs about 38.1 GB of memory at Q8_0 (a 36.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Drex v2.0 Q8 0 – a decision model with 34.7B parameters
Drex v2.0 Q8 0 is a decision model built on Qwen3.6-35B-A3B. It answers typed questions about a given context without generating text. The model runs on Python, llama.cpp or Ollama and supports up to 131,072 context tokens.
Good at
- Fast probability scoring
- No generation needed
- Large context support
Limits
- Requires 36.9 GB GGUF file
- Memory estimate 38.1 GB at 8 k context
- No vision tower loaded
Best for
- Decision‑making tasks
- Email classification
- Game strategy evaluation
Who it’s for. Developers needing a lightweight decision engine for structured queries. It is suitable for integration into applications that require probability outputs without text generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → |
For 48 GB systems, use the Q8_0 GGUF (36.9 GB). If memory is limited to 40 GB, the Q8_0 quant is still the only option. Larger memory budgets allow higher context lengths up to 131,072 tokens.
What GPU do you need for drex v2.0 Q8 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: 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: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which drex v2.0 Q8 0 quant should you choose?
Q8_0 (36.9 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about drex v2.0 Q8 0
How much VRAM does drex v2.0 Q8 0 need?
About 38.1 GB at Q8_0 with an 8K context window. That is the 36.9 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 Q8 0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 38.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of drex v2.0 Q8 0 GGUF?
It depends on the quant: Q8_0 is 36.9 GB.
What context length does drex v2.0 Q8 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 Q8 0 GGUF?
The files are on Hugging Face in the nace-ai/drex-v2.0-Q8_0 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 Q8 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 Q8 0 on 8 GB VRAM?
No, the GGUF file is 36.9 GB and requires about 38.1 GB of RAM at 8 k context.
Does Drex v2.0 support vision inputs?
No, the vision tower is dropped on load; only the language model is used.
What is the maximum context length?
The default limit is 16,384 tokens per request and can be raised to 131,072 tokens.