Modelpublic

Soulfate24/TwIL-LM3-ASHQ1-Remix-GGUF

sourceHugging Faceotherupdated 17d agoView on Hugging Face

0likes3.3kdownloads

Model Card

TwIL-LM3 - 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)	3124 MiB	9.8138	0.0017	1.06%	97.4%	2560 t/s
Fidelity-48pc	2826 MiB	9.8173	0.0024	1.23%	97.0%	2560 t/s
Precision-42pc	2474 MiB	9.8206	0.0037	1.50%	96.4%	2226 t/s
Q6_K-imx (stock)	2414 MiB	9.8629	0.0088	2.54%	93.9%	2695 t/s
Quality-36pc 🥈	2111 MiB	9.9407	0.0144	3.20%	92.5%	3012 t/s
Q5KM-imx (stock)	2111 MiB	9.9407	0.0144	3.20%	92.5%	3012 t/s
Compact-33pc ⭐	1945 MiB	9.9726	0.0242	3.93%	91.2%	2560 t/s
Mini-30pc	1769 MiB	10.0104	0.0327	4.56%	89.9%	2695 t/s
IQ4_XS-imx (stock)	1644 MiB	10.1153	0.0381	4.92%	89.4%	2844 t/s
Nano-27pc	1593 MiB	10.2711	0.0500	5.71%	88.0%	2844 t/s
Pico-24pc	1445 MiB	10.7211	0.0974	7.78%	84.7%	2695 t/s
IQ3_M-imx (stock)	1401 MiB	11.0072	0.1064	8.69%	83.4%	2695 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-RemixDouble-QuantizationSuite