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

Fimbulvetr 11B V2 AWQ by LoneStriker

 »  All LLMs  »  LoneStriker  »  Fimbulvetr 11B V2 AWQ   URL Share it on

  5   

Fimbulvetr 11B V2 AWQ is an open-source language model by LoneStriker. Features: 11b LLM, VRAM: 6GB, Context: 4K, License: cc-by-nc-4.0, Quantized, LLM Explorer Score: 0.12, Arc: 70.1, HellaSwag: 87.8, MMLU: 66.7, GSM8K: 63.7.

  4-bit   Awq   En   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Fimbulvetr-11B-v2-AWQ 

Fimbulvetr 11B V2 AWQ Benchmarks

ARC: 70.14 vs 96.7 (so35)-27.5%
HellaSwag: 87.77 vs 95.3 (gpt4)-7.9%
MMLU: 66.68 vs 88.3 (so35)-24.5%
GSM8K: 63.68 vs 96.4 (so35)-33.9%
LLME Score: 0.12083
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fimbulvetr 11B V2 AWQ (LoneStriker/Fimbulvetr-11B-v2-AWQ)
🌟 Advertise your project 🚀

Fimbulvetr 11B V2 AWQ Parameters and Internals

Additional Notes 
This description contains informal context about personal musings and challenges from the developer.
Supported Languages 
en (unknown)
Input Output 
Input Format:
Alpaca or Vicuna
Release Notes 
Version:
15/2
Notes:
Suitable for Release. Model focused on the submission for the Chai app. Scaling results to Yi/Mixtral soon.
LLM NameFimbulvetr 11B V2 AWQ
Repository 🤗https://huggingface.co/LoneStriker/Fimbulvetr-11B-v2-AWQ 
Base Model(s)  Fimbulvetr 11B V2   Sao10K/Fimbulvetr-11B-v2
Model Size11b
Required VRAM6 GB
Updated2026-07-07
MaintainerLoneStriker
Model Typellama
Model Files  5.0 GB: 1-of-2   1.0 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Fimbulvetr 11B V2 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Synthia V3.0 11B AWQ4K / 6 GB48992
Tengentoppa 11B Instruct AWQ2K / 6.8 GB80
... 11B V2.5 Instruct FP8 Dynamic32K / 11.5 GB322
...istral 11B Omni OPA U1k Ver0.732K / 21.4 GB200
Mistral 11B OP U1k Ver0.732K / 21.4 GB160
Mistral 11B Omni OP U1k Ver0.532K / 21.4 GB190
...istral 11B V2 HQQ 4bit Smashed8K / 6 GB50
...mbulvetr 11B V2.8.0bpw H8 EXL24K / 10.9 GB97
...mbulvetr 11B V2.6.0bpw H6 EXL24K / 8.2 GB24
...mbulvetr 11B V2.3.0bpw H6 EXL24K / 4.3 GB51
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Fimbulvetr-11B-v2-AWQ.

Rank the Fimbulvetr 11B V2 AWQ 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? 54964 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