pplx decider flash v1.2 mixed needs about 4.4 GB of memory at its main file (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.9 GB to 3.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
pplx decider flash v1.2 mixed – 4.84B Qwen3.5‑based decision model
pplx decider flash v1.2 mixed is a 4.84B parameter model distilled from 27B decision models. It supports reasoning and tools, but only text. The model is built on Qwen3.5‑4B and distributed under Apache‑2.0.
Good at
- Reasoning tasks
- Tool‑use queries
- Decision‑making prompts
Limits
- No vision support
- Requires CUDA GPU with ~9 GiB BF16 workspace
- Single‑question prompt only
Best for
- Low‑latency decision queries
- Cost‑sensitive inference
- Embedded LLM use cases
Who it’s for. Developers needing a lightweight decision model that retains most of the 27B model’s accuracy. Suitable for applications where GPU memory is limited and only text input is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.9 GB | 4.4 GB | Fits | Get file → | |
| — | 3.1 GB | 4.6 GB | Fits | Get file → |
The GGUF files are 2.87 GB and 3.06 GB. At 8 k context they need about 4.4 GB and 4.6 GB of VRAM respectively. For 8 GB VRAM use the 2.87 GB build; for 12 GB VRAM the 3.06 GB build is safe. Estimates are approximate.
What GPU do you need for pplx decider flash v1.2 mixed?
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: the best quant that fits is the main file (3.1 GB file, about 4.6 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about pplx decider flash v1.2 mixed
How much VRAM does pplx decider flash v1.2 mixed need?
About 4.4 GB at its main file with an 8K context window. That is the 2.9 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 pplx decider flash v1.2 mixed on an 8 GB GPU?
Yes, with the smaller files: the 3.1 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of pplx decider flash v1.2 mixed GGUF?
It depends on the quant: file is 2.9 GB, file is 3.1 GB.
What context length does pplx decider flash v1.2 mixed 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 pplx decider flash v1.2 mixed GGUF?
The files are on Hugging Face in the Jakevin/pplx-decider-flash-v1.2-mixed-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 flash v1.2 mixed 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 this model on 8 GB VRAM?
Yes, the 2.87 GB GGUF build requires about 4.4 GB VRAM at 8 k context, leaving headroom for working memory.
Does it support image input?
No, the vision tower has been dropped; only text is supported.
What license applies?
Apache License 2.0, as a derivative of perplexity‑ai/pplx‑decider‑flash‑v1.2.