Drex v1.5 needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 9 quants, from 4.6 GB (Q3_K_M) to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Decision model for calibrated probability scoring
Drex v1.5 is an 8.95B‑parameter decision model built on a Qwen3_5ForCausalLM backbone. It reads a state and typed questions and returns probabilities in a single forward pass. The model supports context lengths from 16,384 to 131,072 tokens.
Good at
- Calibrated probability scoring
- Typed question handling
- Long‑context support up to 131k tokens
Limits
- No text generation
- Requires CUDA GPU for full inference
- No vision support
Best for
- Decision‑making APIs
- Agent skill evaluation
- Benchmark scoring
Who it’s for. Developers building decision‑making services that need fast, calibrated probability outputs without text generation. Suitable for API backends and local inference setups using llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 5.4 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_S | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| BF16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8‑GB VRAM use Q4_K_M (5.63 GB) or Q4_K_S (5.35 GB). For 12‑GB VRAM use Q5_K_M (6.47 GB) or Q5_K_S (6.31 GB). For 16‑GB VRAM use Q6_K (7.36 GB) or Q8_0 (9.53 GB). Memory estimates are approximate.
What GPU do you need for Drex v1.5?
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: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).
Which Drex v1.5 quant should you choose?
Q4_K_M is the usual starting point for Drex v1.5: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 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 Q3_K_M at 4.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Drex v1.5
How much VRAM does Drex v1.5 need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Drex v1.5 on an 8 GB GPU?
Yes, with Q5_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Drex v1.5 GGUF?
It depends on the quant: Q3_K_M is 4.6 GB, Q3_K_L is 4.9 GB, Q4_K_S is 5.4 GB, Q4_K_M is 5.6 GB, Q5_K_S is 6.3 GB, Q5_K_M is 6.5 GB and 3 more.
What context length does Drex v1.5 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Drex v1.5 GGUF?
The files are on Hugging Face in the prithivMLmods/drex-v1.5-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 v1.5 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 v1.5 on 8 GB VRAM?
Yes, using the Q4_K_M or Q4_K_S GGUF files which fit within 8 GB VRAM and use about 7 GB of memory at 8k context.
Does Drex v1.5 generate text?
No, it returns calibrated probabilities for typed questions and does not generate free‑form text.