Magnum V2 123B Fp8 Dynamic by leafspark

 ยป  All LLMs  ยป  leafspark  ยป  Magnum V2 123B Fp8 Dynamic   URL Share it on

Base model:anthracite-org/magn... Base model:quantized:anthracit...   Chat   Conversational   De   En   Es   Fp8   Fr   It   Ja   Mistral   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Zh

Magnum V2 123B Fp8 Dynamic Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magnum V2 123B Fp8 Dynamic (leafspark/magnum-v2-123b-fp8-dynamic)

Magnum V2 123B Fp8 Dynamic Parameters and Internals

Model Type 
text-generation
Additional Notes 
Converted to fp8 dynamic by leafspark; quantization took 30 minutes.
Supported Languages 
en (English), fr (French), de (German), es (Spanish), it (Italian), pt (Portuguese), ru (Russian), zh (Chinese), ja (Japanese)
LLM NameMagnum V2 123B Fp8 Dynamic
Repository ๐Ÿค—https://huggingface.co/leafspark/magnum-v2-123b-fp8-dynamic 
Base Model(s)  Magnum V2 123B   anthracite-org/magnum-v2-123b
Model Size123b
Required VRAM123.6 GB
Updated2025-02-15
Maintainerleafspark
Model Typemistral
Model Files  5.0 GB: 1-of-26   4.8 GB: 2-of-26   4.9 GB: 3-of-26   4.8 GB: 4-of-26   4.9 GB: 5-of-26   4.8 GB: 6-of-26   4.9 GB: 7-of-26   4.8 GB: 8-of-26   4.9 GB: 9-of-26   4.8 GB: 10-of-26   4.9 GB: 11-of-26   4.8 GB: 12-of-26   4.9 GB: 13-of-26   4.8 GB: 14-of-26   4.9 GB: 15-of-26   4.8 GB: 16-of-26   4.9 GB: 17-of-26   4.8 GB: 18-of-26   4.9 GB: 19-of-26   4.8 GB: 20-of-26   4.9 GB: 21-of-26   4.8 GB: 22-of-26   4.9 GB: 23-of-26   4.8 GB: 24-of-26   4.9 GB: 25-of-26   2.2 GB: 26-of-26
Supported Languagesen fr de es it pt ru zh ja
Model ArchitectureMistralForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Magnum V2 123B Fp8 Dynamic

Best Alternatives
Context / RAM
Downloads
Likes
Monstral 123B V2128K / 245.4 GB48725
Behemoth 123B V1.2128K / 226.4 GB40222
Behemoth 123B V2.2128K / 226.4 GB36023
Gigaberg Mistral Large 123B128K / 222 GB532
Behemoth 123B V1128K / 221.6 GB37836
Behemoth V1.2 Magnum V4 123B128K / 216.7 GB935
Monstral 123B128K / 221.6 GB22124
Behemoth 123B V1.1128K / 226.4 GB13323
Behemoth V2.2 Magnum V4 123B128K / 221.6 GB471
Behemoth 123B V2.1128K / 226.4 GB2610
Note: green Score (e.g. "73.2") means that the model is better than leafspark/magnum-v2-123b-fp8-dynamic.

Rank the Magnum V2 123B Fp8 Dynamic Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 43186 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227