What are the hardware requirements for MultiMash9 13B Slerp?

MultiMash9 13B Slerp requires approximately 25.7 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 MultiMash9 13B Slerp and how large is it?

MultiMash9 13B Slerp is developed by allknowingroger, a model with 12.9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate MultiMash9 13B Slerp?

MultiMash9 13B Slerp is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MultiMash9 13B Slerp by allknowingroger — VRAM 25.7GB, 32K context

Name: MultiMash9 13B Slerp
Author: allknowingroger

MultiMash9 13B Slerp is an open-source language model by allknowingroger. Features: 12.9b LLM, VRAM: 25.7GB, Context: 32K, License: apache-2.0, MoE, Merged, LLM Explorer Score: 0.18.

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

Model Card on HF 🤗: https://huggingface.co/allknowingroger/MultiMash9-13B-slerp

MultiMash9 13B Slerp Parameters and Internals

Model Type

text-generation

Additional Notes

MultiMash9-13B-slerp is a merge of zhengr/MixTAO-7Bx2-MoE-v8.1 and allknowingroger/Calmex26merge-12B-MoE using LazyMergekit.

LLM Name	MultiMash9 13B Slerp
Repository 🤗	https://huggingface.co/allknowingroger/MultiMash9-13B-slerp
Base Model(s)	zhengr/MixTAO-7Bx2-MoE-v8.1 Calmex26merge 12B MoE zhengr/MixTAO-7Bx2-MoE-v8.1 allknowingroger/Calmex26merge-12B-MoE
Merged Model	Yes
Model Size	12.9b
Required VRAM	25.7 GB
Updated	2025-09-22
Maintainer	allknowingroger
Model Type	mixtral
Model Files	1.0 GB: 1-of-28 0.9 GB: 2-of-28 1.0 GB: 3-of-28 0.9 GB: 4-of-28 0.9 GB: 5-of-28 0.9 GB: 6-of-28 0.9 GB: 7-of-28 0.9 GB: 8-of-28 1.0 GB: 9-of-28 0.9 GB: 10-of-28 0.9 GB: 11-of-28 0.9 GB: 12-of-28 0.9 GB: 13-of-28 0.9 GB: 14-of-28 1.0 GB: 15-of-28 0.9 GB: 16-of-28 0.9 GB: 17-of-28 0.9 GB: 18-of-28 0.9 GB: 19-of-28 0.9 GB: 20-of-28 1.0 GB: 21-of-28 0.9 GB: 22-of-28 0.9 GB: 23-of-28 0.9 GB: 24-of-28 0.9 GB: 25-of-28 0.9 GB: 26-of-28 1.0 GB: 27-of-28 0.8 GB: 28-of-28
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.0
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the MultiMash9 13B Slerp 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 MultiMash9 13B Slerp

Best Alternatives	Context / RAM	Downloads	Likes
MixTAO 7Bx2 MoE V8.1	32K / 25.8 GB	15381	56
Inf Silent Kunoichi V0.1 2x7B	32K / 25.6 GB	8	0
Inf Silent Kunoichi V0.2 2x7B	32K / 25.6 GB	9	1
LogoS 7Bx2 MoE 13B V0.2	32K / 25.9 GB	7978	10
MixTAO 7Bx2 MoE V8.1	32K / 25.8 GB	8760	52
MultiMash8 13B Slerp	32K / 25.7 GB	5	0
MultiMash11 13B Slerp	32K / 25.7 GB	9	0
MultiMash10 13B Slerp	32K / 25.7 GB	8	0
Multimash3 12B Slerp	32K / 25.7 GB	8	0
MixTaoTruthful 13B Slerp	32K / 25.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than allknowingroger/MultiMash9-13B-slerp.