Soulfate24/Ornith-1.5-9B-MTP-ASHQ1-Remix-GGUF overview
Ornith 1.5 9B with MTP ASHQ1 Remix This is a GGUF quantized version of the original model. ๐ Release Benchmarks wiki.test.raw, symmetric FA auto reference | Mโฆ
Runs locally from ~4.9 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| imatrix.gguf | GGUF | GGUF | 4.9 MB | Download |
| mmproj-ASHQ1-Balanced-72pc.gguf | GGUF | GGUF | 631.2 MB | Download |
| model-ASHQ1-Compact-33pc.gguf | GGUF | GGUF | 5.81 GB | Download |
| model-ASHQ1-Fidelity-48pc.gguf | GGUF | GGUF | 8.24 GB | Download |
| model-ASHQ1-Mini-30pc.gguf | GGUF | GGUF | 5.44 GB | Download |
| model-ASHQ1-Nano-27pc.gguf | GGUF | GGUF | 4.64 GB | Download |
| model-ASHQ1-Pico-24pc.gguf | GGUF | GGUF | 4.29 GB | Download |
| model-ASHQ1-Precision-42pc.gguf | GGUF | GGUF | 7.38 GB | Download |
| model-ASHQ1-Quality-36pc.gguf | GGUF | GGUF | 6.24 GB | Download |
Model Details
| Model ID | Soulfate24/Ornith-1.5-9B-MTP-ASHQ1-Remix-GGUF |
|---|---|
| Author | Soulfate24 |
| Pipeline | text-generation |
| License | mit |
| Base model | ornith-ai/Ornith-1.5-9B |
| Last modified | 2026-09-10T10:31:21.000Z |
Model README
---
library_name: transformers
license: mit
license_link: https://huggingface.co/ornith-ai/Ornith-1.5-9B/blob/main/LICENSE
pipeline_tag: text-generation
base_model:
- ornith-ai/Ornith-1.5-9B
tags:
- quantization
- gguf
- ashq1
- imatrix
---
Ornith-1.5-9B with MTP - ASHQ1-Remix
This is a GGUF quantized version of the original model.
๐ Release Benchmarks (wiki.test.raw, symmetric FA-auto reference)
| Model | Size | PPL | KLD | RMS ฮp | top-p | Speed |
| :--- | ---: | ---: | ---: | ---: | ---: | ---: |
| Q8_0 (stock) | 9333 MiB | 9.0824 | 0.0058 | 2.26% | 97.9% | 244 t/s |
| Fidelity-48pc | 8436 MiB | 9.0227โ | 0.0087 | 2.58% | 97.2% | 260 t/s |
| Precision-42pc | 7554 MiB | 8.9957โ | 0.0094 | 2.72% | 96.8% | 324 t/s |
| Q6_K-imx (stock) | 7209 MiB | 8.9836โ | 0.0107 | 2.90% | 96.4% | 320 t/s |
| Quality-36pc | 6388 MiB | 8.9895โ | 0.0241 | 4.22% | 94.5% | 1313 t/s |
| Q5_K_M-imx (stock) | 6335 MiB | 8.6345โ | 0.0665 | 6.48% | 90.7% | 1219 t/s |
| Compact-33pc โญ | 5945 MiB | 9.1332 | 0.0319 | 4.88% | 93.1% | 1219 t/s |
| Mini-30pc ๐ฅ | 5566 MiB | 9.0189โ | 0.0425 | 5.65% | 91.8% | 1384 t/s |
| IQ4_XS-imx (stock) | 5080 MiB | 9.2758 | 0.0538 | 6.29% | 90.7% | 1506 t/s |
| Nano-27pc | 4750 MiB | 9.5968 | 0.0802 | 7.57% | 87.9% | 1249 t/s |
| Pico-24pc | 4389 MiB | 9.5871 | 0.1202 | 9.25% | 85.1% | 1384 t/s |
| IQ3_M-imx (stock) | 4313 MiB | 9.5973 | 0.1421 | 10.46% | 84.3% | 1384 t/s |
โน๏ธ About ASHQ1-Remix Suite
Activation-aware GGUF quantization whose every ratio, floor, and cap traces to a measured experiment. Plain-BF16-native first; AutoRound lineage supported with explicit saturation bounds. Full seven-tier ladder validated across six model families.
๐ Link: https://huggingface.co/Soulfate24/AutoRound-ASHQ1-Remix_Double-Quantization_Suite
Run Soulfate24/Ornith-1.5-9B-MTP-ASHQ1-Remix-GGUF with guIDE
Download guIDE โ the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face ยท Compare models