Soulfate24/MiniCPM5-1B-ASHQ1-Remix-GGUF overview
MiniCPM5 1B ASHQ1 Remix This is a GGUF quantized version of the original model. 📈 Release Benchmarks wiki.test.raw, symmetric FA auto reference | Model | Size…
Runs locally from ~1.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| imatrix.gguf | GGUF | GGUF | 1.3 MB | Download |
| model-ASHQ1-Compact-33pc.gguf | GGUF | GGUF | 686.9 MB | Download |
| model-ASHQ1-Fidelity-48pc.gguf | GGUF | GGUF | 996.8 MB | Download |
| model-ASHQ1-Mini-30pc.gguf | GGUF | GGUF | 624.9 MB | Download |
| model-ASHQ1-Nano-27pc.gguf | GGUF | GGUF | 562.9 MB | Download |
| model-ASHQ1-Pico-24pc.gguf | GGUF | GGUF | 503.3 MB | Download |
| model-ASHQ1-Precision-42pc.gguf | GGUF | GGUF | 896.8 MB | Download |
| model-ASHQ1-Quality-36pc.gguf | GGUF | GGUF | 750.4 MB | Download |
Model Details
| Model ID | Soulfate24/MiniCPM5-1B-ASHQ1-Remix-GGUF |
|---|---|
| Author | Soulfate24 |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | openbmb/MiniCPM5-1B |
| Last modified | 2026-09-10T10:52:33.000Z |
Model README
---
license: apache-2.0
language:
- en
- zh
library_name: transformers
pipeline_tag: text-generation
datasets:
- openbmb/Ultra-FineWeb
- openbmb/Ultra-FineWeb-L3
- openbmb/UltraData-Math
- openbmb/UltraData-SFT-2605
base_model:
- openbmb/MiniCPM5-1B
tags:
- minicpm
- minicpm5
- llama
- text-generation
- long-context
- tool-calling
- on-device
- edge-ai
- quantization
- gguf
- ashq1
- imatrix
---
MiniCPM5-1B - 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) | 1100 MiB | 26.9046 | 0.0019 | 0.96% | 97.2% | 5689 t/s |
| Fidelity-48pc | 997 MiB | 27.0943 | 0.0056 | 1.66% | 95.3% | 5689 t/s |
| Precision-42pc 🥈 | 897 MiB | 27.1550 | 0.0074 | 1.84% | 94.5% | 5689 t/s |
| Q6_K-imx (stock) | 851 MiB | 27.1517 | 0.0079 | 1.91% | 94.3% | 5689 t/s |
| Quality-36pc ⭐ | 750 MiB | 27.6966 | 0.0279 | 3.70% | 90.1% | 5120 t/s |
| Q5_K_M-imx (stock) | 750 MiB | 27.6966 | 0.0279 | 3.70% | 90.1% | 5689 t/s |
| Compact-33pc | 687 MiB | 27.6945 | 0.0775 | 6.01% | 83.7% | 5120 t/s |
| Mini-30pc | 625 MiB | 28.8936 | 0.1154 | 7.27% | 80.8% | 5120 t/s |
| IQ4_XS-imx (stock) | 609 MiB | 29.1625 | 0.1096 | 7.13% | 81.0% | 5689 t/s |
| Nano-27pc | 563 MiB | 28.9311 | 0.1355 | 7.98% | 78.9% | 5689 t/s |
| IQ3_M-imx (stock) | 536 MiB | 36.0620 | 0.3241 | 13.66% | 69.2% | 5120 t/s |
| Pico-24pc ✗ | 503 MiB | 37.4572 | 0.3886 | 14.66% | 66.2% | 5689 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/MiniCPM5-1B-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