Candle Mistral 7B Instruct V0.2 is an open-source language model by DanielClough. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, HF Score: 65.7, LLM Explorer Score: 0.24, ELO: 1072, Arc: 63.1, HellaSwag: 84.9, MMLU: 60.8, TruthfulQA: 68.3, WinoGrande: 77.2, GSM8K: 40.
Dataset:mistralai/mistral-7b-i... En Endpoints compatible Gguf Instruct Mistral Q4 Quantized Region:us Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/DanielClough/Candle_Mistral-7B-Instruct-v0.2
Candle Mistral 7B Instruct V0.2 Benchmarks
LMSys ELO: 1072 vs 1272 (so35)-15.7%
ARC: 63.14 vs 96.7 (so35)-34.7%
HellaSwag: 84.88 vs 95.3 (gpt4)-10.9%
MMLU: 60.78 vs 88.3 (so35)-31.2%
TruthfulQA: 68.26 vs 59 (gpt4)15.7%
WinoGrande: 77.19 vs 87.5 (gpt4)-11.8%
GSM8K: 40.03 vs 96.4 (so35)-58.5%
LLME Score: 0.23775
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 Mistral 7B Instruct V0.2 Parameters and Internals
| LLM Name | Candle Mistral 7B Instruct V0.2 |
| Repository 🤗 | https://huggingface.co/DanielClough/Candle_Mistral-7B-Instruct-v0.2 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2026-01-16 |
| Maintainer | DanielClough |
| Model Type | mistral |
| Instruction-Based | Yes |
| 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 | 4.36.0 |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Candle Mistral 7B Instruct V0.2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 7B Instruct V0.2.gguf | 32K / 14.5 GB | 17 | 3 |
| Mistral 7B Instruct V0.2 GGUF | 32K / 4.4 GB | 36 | 2 |
| Tamil Mistral 7B Instruct V0.1 | 32K / 14.8 GB | 230 | 14 |
| Mistral V0.3 7B Cybersecurity | 32K / 14.5 GB | 30 | 1 |
| BioMistralMerged | 32K / 14.4 GB | 55 | 2 |
| Mistral 7B Instruct V0.3 GGUF | 32K / 2.7 GB | 145 | 1 |
| Mistral 7B Instruct V0.3 GGUF | 32K / 2.7 GB | 124 | 1 |
| ...tral 7B V0.3 Chinese Chat 4bit | 32K / 4.1 GB | 76 | 2 |
| ...tral 7B V0.3 Chinese Chat 8bit | 32K / 7.7 GB | 38 | 2 |
| ...stral 7B V0.3 Chinese Chat F16 | 32K / 14.5 GB | 35 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_Mistral-7B-Instruct-v0.2 .
Rank the Candle Mistral 7B Instruct V0.2 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? 53151 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