What are the hardware requirements for HuginnV5.5 12.6B?

HuginnV5.5 12.6B requires approximately 25.8 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 HuginnV5.5 12.6B and how large is it?

HuginnV5.5 12.6B is developed by The-Face-Of-Goonery, a model with 12.6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does HuginnV5.5 12.6B perform on standard benchmarks?

HuginnV5.5 12.6B has the following published scores: MMLU 64.5. Compare against reference models on this page or on the LLM Explorer leaderboards.

HuginnV5.5 12.6B by The-Face-Of-Goonery — VRAM 25.8GB, 32K context

Name: HuginnV5.5 12.6B
Rating: 1.4 (5 reviews)
Author: The-Face-Of-Goonery

HuginnV5.5 12.6B is an open-source language model by The-Face-Of-Goonery. Features: 12.6b LLM, VRAM: 25.8GB, Context: 32K, License: cc-by-4.0, Quantized, HF Score: 72.9, LLM Explorer Score: 0.26, Arc: 72, HellaSwag: 86.7, MMLU: 64.5, TruthfulQA: 70.5, WinoGrande: 81.3, GSM8K: 62.6.

Autotrain compatible Conversational Endpoints compatible Gguf License:cc-by-4.0 Mistral Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/The-Face-Of-Goonery/HuginnV5.5-12.6B

HuginnV5.5 12.6B Benchmarks

ARC: 72.01 vs 96.7 (so35)^-25.5%

HellaSwag: 86.7 vs 95.3 (gpt4)^-9%

MMLU: 64.5 vs 88.3 (so35)^-27%

TruthfulQA: 70.45 vs 59 (gpt4)^19.4%

WinoGrande: 81.29 vs 87.5 (gpt4)^-7.1%

GSM8K: 62.62 vs 96.4 (so35)^-35%

LLME Score: 0.25794

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

HuginnV5.5 12.6B (The-Face-Of-Goonery/HuginnV5.5-12.6B)

🌟 Advertise your project 🚀

HuginnV5.5 12.6B Parameters and Internals

LLM Name	HuginnV5.5 12.6B
Repository 🤗	https://huggingface.co/The-Face-Of-Goonery/HuginnV5.5-12.6B
Model Size	12.6b
Required VRAM	25.8 GB
Updated	2024-07-04
Maintainer	The-Face-Of-Goonery
Model Type	mistral
Model Files	7.3 GB 3.2 GB 7.3 GB 9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.0 GB: 3-of-3
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	MistralForCausalLM
License	cc-by-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Best Alternatives to HuginnV5.5 12.6B

Best Alternatives	Context / RAM	Downloads	Likes
...al Nemo Instruct 2407 Bnb 4bit	128K / 8.3 GB	17568	31
...istral Nemo Base 2407 Bnb 4bit	128K / 8.3 GB	3607	15
...uginnV5.5 12.6B 8.0bpw H8 EXL2	32K / 13.1 GB	3	1

Rank the HuginnV5.5 12.6B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53232 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

HuginnV5.5 12.6B by The-Face-Of-Goonery

» All LLMs » The-Face-Of-Goonery » HuginnV5.5 12.6B URL Share it on

HuginnV5.5 12.6B Benchmarks

HuginnV5.5 12.6B Parameters and Internals

Best Alternatives to HuginnV5.5 12.6B

Rank the HuginnV5.5 12.6B Capabilities

What open-source LLMs or SLMs are you in search of? 53232 in total.