Orca Mini V3 7B is an open-source language model by psmathur. Features: 7b LLM, VRAM: 13.5GB, Context: 4K, License: other, Quantized, HF Score: 53.5, LLM Explorer Score: 0.17, Arc: 56.9, HellaSwag: 79.6, MMLU: 52.4, TruthfulQA: 50.5, WinoGrande: 74.3, GSM8K: 7.1.
Arxiv:2302.13971 Arxiv:2306.02707 Dataset:ehartford/dolphin Dataset:psmathur/orca mini v1 ... En Endpoints compatible Fp16 Llama Model-index Pytorch Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/pankajmathur/orca_mini_v3_7b
Orca Mini V3 7b Benchmarks
MMLU Pro: 12.04
MUSR: 22.71
BBH: 17.84
IFEval: 28.21 vs 88 (so35)-67.9%
ARC: 56.91 vs 96.7 (so35)-41.1%
HellaSwag: 79.64 vs 95.3 (gpt4)-16.4%
MMLU: 52.37 vs 88.3 (so35)-40.7%
TruthfulQA: 50.51 vs 59 (gpt4)-14.4%
WinoGrande: 74.27 vs 87.5 (gpt4)-15.1%
GSM8K: 7.13 vs 96.4 (so35)-92.6%
MATH Lvl 5: 1.06
LLME Score: 0.17439
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)
Orca Mini V3 7B Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Orca Mini V3 7b |
| Repository 🤗 | https://huggingface.co/pankajmathur/orca_mini_v3_7b |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 13.5 GB |
| Updated | 2026-04-10 |
| Maintainer | psmathur |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | fp16 |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.32.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Orca Mini V3 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Smaugv0.1 6.0bpw H6 EXL2 | 195K / 26.4 GB | 3 | 4 |
| Smaugv0.1 5.0bpw H6 EXL2 | 195K / 22.3 GB | 4 | 3 |
| Smaugv0.1 3.0bpw H6 EXL2 | 195K / 13.9 GB | 4 | 1 |
| Smaugv0.1 4.0bpw H6 EXL2 | 195K / 18 GB | 3 | 1 |
| Smaugv0.1 4.65bpw H6 EXL2 | 195K / 20.8 GB | 3 | 1 |
| Smaugv0.1 8.0bpw H8 EXL2 | 195K / 34.9 GB | 3 | 1 |
| DeepSeek Prover V2 7B 4bit | 64K / 3.9 GB | 64 | 4 |
| Mistral 7B Openplatypus 1K | 32K / 29 GB | 1814 | 0 |
| Mistral 7B OpenOrca 1K | 32K / 29 GB | 1811 | 3 |
| ...rnlm2 20B Llama 4.0bpw H6 EXL2 | 32K / 11 GB | 1 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than pankajmathur/orca_mini_v3_7b .
Rank the Orca Mini V3 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