LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Magnum V2 123B Fp8 Dynamic by leafspark

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

  6   

Magnum V2 123B Fp8 Dynamic is an open-source language model by leafspark. Features: 123b LLM, VRAM: 123.6GB, Context: 128K, License: other, LLM Explorer Score: 0.15.

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
Model Card on HF 🤗: https://huggingface.co/leafspark/magnum-v2-123b-fp8-dynamic 

Magnum V2 123B Fp8 Dynamic Benchmarks

LLME Score: 0.15214
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)
🌟 Advertise your project 🚀

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 🤗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
Updated2026-04-07
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
Behemoth X R1 123B128K / 216.7 GB3900
Behemoth R1 123B V2128K / 226.4 GB115920
Behemoth X 123B V2128K / 217.2 GB76316
Behemoth ReduX 123B V1128K / 217.2 GB3468
ML2 123B Magnum Diamond128K / 212.4 GB1111
Gigaberg Mistral Large 123B128K / 222 GB62
Monstral 123B V2128K / 245.4 GB2943
Behemoth 123B V1.2128K / 226.4 GB3330
Behemoth 123B V2.2128K / 226.4 GB1127
Behemoth 123B V2.1128K / 226.4 GB6510
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

🆘 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? 52721 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