What are the hardware requirements for TaoPassthrough 15B S?

TaoPassthrough 15B S requires approximately 38.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TaoPassthrough 15B S and how large is it?

TaoPassthrough 15B S is developed by allknowingroger, a model with 19.2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does TaoPassthrough 15B S perform on standard benchmarks?

TaoPassthrough 15B S has the following published scores: MMLU 64.26. Compare against reference models on this page or on the LLM Explorer leaderboards.

TaoPassthrough 15B S by allknowingroger — VRAM 38.4GB, 32K context

Name: TaoPassthrough 15B S
Author: allknowingroger

TaoPassthrough 15B S is an open-source language model by allknowingroger. Features: 19.2b LLM, VRAM: 38.4GB, Context: 32K, License: apache-2.0, MoE, Merged, LLM Explorer Score: 0.12, Arc: 71.8, HellaSwag: 88.9, MMLU: 64.3, GSM8K: 50.

Merged Model Autotrain compatible Base model:finetune:mixtao/mix... Base model:mixtao/mixtao-7bx2-... Endpoints compatible Mixtral Moe Region:us Safetensors Sharded Tensorflow Zhengr/mixtao-7bx2-moe-v8.1

Model Card on HF 🤗: https://huggingface.co/allknowingroger/TaoPassthrough-15B-s

TaoPassthrough 15B S Parameters and Internals

Additional Notes

The model is a merge of the same base model repeated five times using LazyMergekit with passthrough method.

LLM Name	TaoPassthrough 15B S
Repository 🤗	https://huggingface.co/allknowingroger/TaoPassthrough-15B-s
Base Model(s)	zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1 zhengr/MixTAO-7Bx2-MoE-v8.1
Merged Model	Yes
Model Size	19.2b
Required VRAM	38.4 GB
Updated	2025-09-22
Maintainer	allknowingroger
Model Type	mixtral
Model Files	2.0 GB: 1-of-20 1.9 GB: 2-of-20 2.0 GB: 3-of-20 2.0 GB: 4-of-20 2.0 GB: 5-of-20 2.0 GB: 6-of-20 1.9 GB: 7-of-20 2.0 GB: 8-of-20 2.0 GB: 9-of-20 2.0 GB: 10-of-20 2.0 GB: 11-of-20 2.0 GB: 12-of-20 2.0 GB: 13-of-20 2.0 GB: 14-of-20 2.0 GB: 15-of-20 2.0 GB: 16-of-20 2.0 GB: 17-of-20 2.0 GB: 18-of-20 2.0 GB: 19-of-20 0.6 GB: 20-of-20
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	float16

Rank the TaoPassthrough 15B S capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to TaoPassthrough 15B S

Best Alternatives	Context / RAM	Downloads	Likes
MixTAO 19B Pass	32K / 38.1 GB	3	2
Lorge 2x7B UAMM	32K / 38.2 GB	16	0
Multimerge 19B Pass	32K / 38 GB	10	0
Mistralmath 15B Pass	32K / 38.5 GB	11	0
Raccoon Small	32K / 38.4 GB	60	1
SPEED 1 BASE	4K / 38.4 GB	172	2
Mixtral 11Bx2 MoE 19B	4K / 38.4 GB	102	38
...oundary Solar Chat 2x10.7B MoE	4K / 38 GB	123	1
SunnyRain 2x10.7B	4K / 38.4 GB	10	0
19B MATH DPO	4K / 38.4 GB	53	0

Note: green Score (e.g. "73.2") means that the model is better than allknowingroger/TaoPassthrough-15B-s.