pplx decider v1.1 27b needs about 22.4 GB of memory at Q5_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 0.0 GB to 27.2 GB (Q8_0).
27B decision model with bidirectional attention and calibrated probabilities
pplx decider v1.1 27b is a decision‑only model based on Qwen3.5‑27B. It returns calibrated probabilities for typed questions about a shared state. The model uses a noncausal full‑attention mode for 16 of 64 layers and linear attention for the rest.
Good at
- Accurate decision making with calibrated scores
- Handles Czech case marking and word order better than causal models
- Supports image inputs up to 2048×2048 pixels
Limits
- Requires 8,192‑token context; over 8,192 tokens it refuses
- No text generation, only decision outputs
- Dense 27B model needs large VRAM for full inference
Best for
- Decision‑making in conversational agents
- Evaluating state‑dependent questions
- Image‑guided decision tasks
Who it’s for. Developers building decision‑oriented applications that need calibrated probabilities. The model is suitable for systems that can handle a 27B dense model and require accurate, non‑generative outputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_M | 19.6 GB | 22.4 GB | Too big | Get file → | |
| Q8_0 | 27.2 GB | 31.0 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q5_K_M quant (19.58 GB file, ~22.4 GB memory at 8k context). For 16‑GB VRAM, Q8_0 (27.25 GB file, ~31 GB memory) is available but will exceed 16 GB. The unknown quant is only 0.01 GB but memory usage is not specified.
What GPU do you need for pplx decider v1.1 27b?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.6 GB file, about 22.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (27.2 GB file, about 31.0 GB in use).
Which pplx decider v1.1 27b quant should you choose?
Q5_K_M (19.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 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 pplx decider v1.1 27b
How much VRAM does pplx decider v1.1 27b need?
About 22.4 GB at Q5_K_M with an 8K context window. That is the 19.6 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 pplx decider v1.1 27b on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of pplx decider v1.1 27b GGUF?
It depends on the quant: file is 0.0 GB, Q5_K_M is 19.6 GB, Q8_0 is 27.2 GB.
Where can I download pplx decider v1.1 27b GGUF?
The files are on Hugging Face in the Livesport/pplx-decider-v1.1-27b-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 pplx decider v1.1 27b 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 pplx decider v1.1 27b on 8 GB VRAM?
Only the Q5_K_M quant is feasible on 8 GB VRAM, as it requires ~22.4 GB of memory at 8k context. The model will not fit on 8 GB VRAM without further quantization.
Does this model support image inputs?
Yes, it accepts images up to 2048×2048 pixels. Each 32×32 patch counts as one visual token.
What happens if I exceed 8,192 tokens?
The model refuses the request and returns an error; it does not truncate the input.