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

Candle SOLAR 10.7B Instruct V1.0 by DanielClough

 »  All LLMs  »  DanielClough  »  Candle SOLAR 10.7B Instruct V1.0   URL Share it on

  78   

Candle SOLAR 10.7B Instruct V1.0 is an open-source language model by DanielClough. Features: 10.7b LLM, VRAM: 21.4GB, Context: 4K, License: apache-2.0, Quantized, Instruction-Based, HF Score: 68, LLM Explorer Score: 0.12, Arc: 64.2, HellaSwag: 82.6, MMLU: 65.7, TruthfulQA: 56, WinoGrande: 81.1, GSM8K: 58.4.

Dataset:upstage/solar-10.7b-in...   En   Endpoints compatible   Gguf   Instruct   Llama   Q4   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DanielClough/Candle_SOLAR-10.7B-Instruct-v1.0 

Candle SOLAR 10.7B Instruct V1.0 Benchmarks

ARC: 64.16 vs 96.7 (so35)-33.7%
HellaSwag: 82.62 vs 95.3 (gpt4)-13.3%
MMLU: 65.71 vs 88.3 (so35)-25.6%
TruthfulQA: 55.95 vs 59 (gpt4)-5.2%
WinoGrande: 81.06 vs 87.5 (gpt4)-7.4%
GSM8K: 58.38 vs 96.4 (so35)-39.4%
LLME Score: 0.12328
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Candle SOLAR 10.7B Instruct V1.0 (DanielClough/Candle_SOLAR-10.7B-Instruct-v1.0)
🌟 Advertise your project 🚀

Candle SOLAR 10.7B Instruct V1.0 Parameters and Internals

Model Type 
text-generation
Additional Notes 
This repo includes `.gguf` built for HuggingFace/Candle.
Supported Languages 
en (high)
LLM NameCandle SOLAR 10.7B Instruct V1.0
Repository 🤗https://huggingface.co/DanielClough/Candle_SOLAR-10.7B-Instruct-v1.0 
Base Model(s)  Minjae99/solar-10.7b-v1.0_adapter   Minjae99/solar-10.7b-v1.0_adapter
Model Size10.7b
Required VRAM21.4 GB
Updated2026-04-03
MaintainerDanielClough
Model Typellama
Instruction-BasedYes
Model Files  21.5 GB   3.5 GB   4.6 GB   6.0 GB   6.7 GB   6.0 GB   7.4 GB   8.1 GB   7.4 GB   8.8 GB   11.4 GB   12.1 GB   12.2 GB   4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Supported Languagesen
GGUF QuantizationYes
Quantization Typeq4|gguf
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.35.0
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Candle SOLAR 10.7B Instruct V1.0

Best Alternatives
Context / RAM
Downloads
Likes
SOLAR 10.7B Instruct V1.0 GGUF4K / 4.5 GB862
... 10.7B Instruct V1.0 128K EXL2128K / 5.6 GB21
UNA SOLAR 10.7B Instruct V1.04K / 21.4 GB6516
Eclectus 1.1 Dedup4K / 21.4 GB70
Eclectus1.14K / 21.4 GB50
Solar 10.7B SLERP EXL24K / 5.6 GB84
...Instruct V1.0 6.0bpw H6 EXL2 24K / 8.2 GB12
...Instruct V1.0 8.0bpw H8 EXL2 24K / 10.8 GB31
...Instruct V1.0 3.0bpw H6 EXL2 24K / 4.3 GB70
SOLAR 10.7B Instruct V1.0 128K128K / 21.4 GB1243
Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_SOLAR-10.7B-Instruct-v1.0.

Rank the Candle SOLAR 10.7B Instruct V1.0 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? 52758 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