Koshkasa/Vortex5_Phoenix-X-26B-A4B-IQ4_NL-GGUF overview
What's that? Mixed precision mainly IQ4 NL quantization of Vortex5/Phoenix X 26B A4B https://huggingface.co/Vortex5/Phoenix X 26B A4B . Precision was quanted u…
Runs locally from ~54.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | Koshkasa/Vortex5_Phoenix-X-26B-A4B-IQ4_NL-GGUF |
|---|---|
| Author | Koshkasa |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | Vortex5/Phoenix-X-26B-A4B |
| Last modified | 2026-08-13T13:49:02.000Z |
Model README
---
license: apache-2.0
base_model:
- Vortex5/Phoenix-X-26B-A4B
library_name: llama.cpp
pipeline_tag: text-generation
tags:
- gguf
- quantized
- llama.cpp
- roleplay
- mixed precision
- iq4_nl
quantized_by: Koshkasa
base_model_relation: quantized
---
What's that?
Mixed precision mainly IQ4_NL quantization of Vortex5/Phoenix-X-26B-A4B. Precision was quanted up to Q6_K in 3 beginning and end layers, as well as global attn layers, resulting in 10/30 attn-related tensor groups being Q6_K.
IQ4_NL was chosen specifically for outlier handling. In my testing, even IQ4_XS does break MoE occasionally, unless you're building it from a QAT checkpoint.
Deliberately stepping away from mixed math/article/story/rp soup datasets, imatrix dataset is a random conversation 250000-token prune of Squish42/bluemoon-fandom-1-1-rp-cleaned.
Disclosure
My only contribution is compute. This is neither my merge nor my dataset. WYSIWYG. Have fun.
Model card incomplete. Tests and comparisons may be uploaded at a later date.
Run Koshkasa/Vortex5_Phoenix-X-26B-A4B-IQ4_NL-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models