Candle Dolphin 2.2.1 Mistral 7B is an open-source language model by DanielClough. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Quantized, HF Score: 65, LLM Explorer Score: 0.24, ELO: 1151, Arc: 88.2, HellaSwag: 79.7, MMLU: 62.9, TruthfulQA: 53.1, WinoGrande: 78.6, GSM8K: 61.9.
Dataset:ehartford/dolphin-2.2.... En Endpoints compatible Gguf Mistral Q4 Quantized Region:us Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/DanielClough/Candle_dolphin-2.2.1-mistral-7b
Candle Dolphin 2.2.1 Mistral 7B Benchmarks
LMSys ELO: 1151 vs 1272 (so35)-9.5%
ARC: 88.2 vs 96.7 (so35)-8.8%
HellaSwag: 79.7 vs 95.3 (gpt4)-16.4%
MMLU: 62.9 vs 88.3 (so35)-28.8%
TruthfulQA: 53.14 vs 59 (gpt4)-9.9%
WinoGrande: 78.61 vs 87.5 (gpt4)-10.2%
GSM8K: 61.9 vs 96.4 (so35)-35.8%
OpenCompas: 58 vs 73.3 (gpt4)-20.9%
Exam: 66.7 vs 77.2 (gpt4)-13.6%
Language: 39.8 vs 62 (gpt4)-35.8%
Knowledge: 58.4 vs 73.5 (gpt4)-20.5%
Understand: 68.7 vs 70 (gpt4)-1.9%
Reasoning: 56.8 vs 74.4 (gpt4)-23.7%
LLME Score: 0.2412
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)
Candle Dolphin 2.2.1 Mistral 7B Parameters and Internals
| Model Type |
| |
| Additional Notes |
| |
| Supported Languages |
|
| LLM Name | Candle Dolphin 2.2.1 Mistral 7B |
| Repository 🤗 | https://huggingface.co/DanielClough/Candle_dolphin-2.2.1-mistral-7b |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2026-04-05 |
| Maintainer | DanielClough |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.34.1 |
| Vocabulary Size | 32002 |
| Torch Data Type | bfloat16 |
Best Alternatives to Candle Dolphin 2.2.1 Mistral 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MegaBeam Mistral 7B 300K Gguf | 282K / 5 GB | 35 | 3 |
| MegaBeam Mistral 7B 300K Gguf | 282K / 5 GB | 13 | 3 |
| Mistral 7B Instruct V0.2.gguf | 32K / 14.5 GB | 17 | 3 |
| Mistral 7B Instruct V0.2 GGUF | 32K / 4.4 GB | 36 | 2 |
| ...andle Mistral 7B Instruct V0.2 | 32K / 14.4 GB | 15 | 0 |
| Boptruth Agatha 7B | 32K / 14.4 GB | 28 | 0 |
| Mahou 1.2a Mistral 7B | 32K / 14.4 GB | 31 | 7 |
| Moxin 7B LLM | 32K / 0.9 GB | 1096 | 19 |
| Moxin Chat 7B | 32K / 0.9 GB | 290 | 32 |
| Tamil Mistral 7B Instruct V0.1 | 32K / 14.8 GB | 211 | 14 |
Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_dolphin-2.2.1-mistral-7b .
Rank the Candle Dolphin 2.2.1 Mistral 7B 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! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a