Soulfate24/Nanbeige4.2-3B-DSpark-ASHQ1-Remix-GGUF overview
Nanbeige4.2 3B with DSpark ASHQ1 Remix This is a GGUF quantized version of the original model. 📈 Release Benchmarks wiki.test.raw, symmetric FA auto reference…
Runs locally from ~2.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| dspark-ASHQ1-Quality-36pc.gguf | GGUF | GGUF | 607.2 MB | Download |
| imatrix.gguf | GGUF | GGUF | 2.7 MB | Download |
| model-ASHQ1-Compact-33pc.gguf | GGUF | GGUF | 2.57 GB | Download |
| model-ASHQ1-Fidelity-48pc.gguf | GGUF | GGUF | 3.73 GB | Download |
| model-ASHQ1-Mini-30pc.gguf | GGUF | GGUF | 2.33 GB | Download |
| model-ASHQ1-Nano-27pc.gguf | GGUF | GGUF | 2.10 GB | Download |
| model-ASHQ1-Pico-24pc.gguf | GGUF | GGUF | 1.87 GB | Download |
| model-ASHQ1-Precision-42pc.gguf | GGUF | GGUF | 3.30 GB | Download |
| model-ASHQ1-Quality-36pc.gguf | GGUF | GGUF | 2.78 GB | Download |
Model Details
| Model ID | Soulfate24/Nanbeige4.2-3B-DSpark-ASHQ1-Remix-GGUF |
|---|---|
| Author | Soulfate24 |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | Nanbeige/Nanbeige4.2-3B,Nanbeige/Nanbeige4.2-3B-DSpark |
| Last modified | 2026-09-10T13:29:52.000Z |
Model README
---
license: apache-2.0
language:
- en
- zh
library_name: transformers
pipeline_tag: text-generation
base_model:
- Nanbeige/Nanbeige4.2-3B
- Nanbeige/Nanbeige4.2-3B-DSpark
tags:
- llm
- nanbeige
- dspark
- quantization
- gguf
- ashq1
- imatrix
---
Nanbeige4.2-3B with DSpark - ASHQ1-Remix
This is a GGUF quantized version of the original model.
📈 Release Benchmarks (wiki.test.raw, symmetric FA-auto reference)
| Model | Size | PPL | KLD | RMS Δp | top-p | Speed |
| :--- | ---: | ---: | ---: | ---: | ---: | ---: |
| Q8_0 (stock) | 4229 MiB | 34.4742 | 0.0105 | 2.39% | 95.6% | 353 t/s |
| Fidelity-48pc 🥈 | 3824 MiB | 34.3246† | 0.0247 | 3.42% | 94.0% | 371 t/s |
| Precision-42pc ⭐ | 3384 MiB | 34.3791† | 0.0331 | 3.94% | 92.5% | 382 t/s |
| Q6_K-imx (stock) | 3266 MiB | 34.4411† | 0.0335 | 3.99% | 92.4% | 406 t/s |
| Quality-36pc | 2849 MiB | 34.6224 | 0.0743 | 5.80% | 88.3% | 466 t/s |
| Q5_K_M-imx (stock) | 2849 MiB | 34.6224 | 0.0743 | 5.80% | 88.3% | 470 t/s |
| Compact-33pc | 2630 MiB | 34.6636 | 0.1441 | 7.98% | 83.8% | 512 t/s |
| Mini-30pc | 2391 MiB | 33.5214† | 0.1728 | 8.66% | 81.8% | 557 t/s |
| IQ4_XS-imx (stock) | 2268 MiB | 34.8506 | 0.1813 | 9.17% | 81.2% | 457 t/s |
| Nano-27pc ✗ | 2152 MiB | 33.7551† | 0.2191 | 10.12% | 78.6% | 453 t/s |
| IQ3_M-imx (stock) | 1985 MiB | 36.4366 | 0.4492 | 14.31% | 70.5% | 539 t/s |
| Pico-24pc ✗ | 1913 MiB | 37.8642 | 0.3878 | 13.31% | 72.6% | 545 t/s |
ℹ️ 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.
🔗 Link: https://huggingface.co/Soulfate24/AutoRound-ASHQ1-Remix_Double-Quantization_Suite
Run Soulfate24/Nanbeige4.2-3B-DSpark-ASHQ1-Remix-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models