Miqu 6B Truthy is an open-source language model by vicgalle. Features: 6b LLM, VRAM: 11.3GB, Context: 31K, License: apache-2.0, HF Score: 30.3, LLM Explorer Score: 0.17, Arc: 27.7, HellaSwag: 26.7, MMLU: 27, TruthfulQA: 50.6, WinoGrande: 49.6.
Conversational Dataset:jondurbin/truthy-dpo-v... Endpoints compatible Llama Miqu Model-index Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/vicgalle/Miqu-6B-truthy
Miqu 6B Truthy Benchmarks
ARC: 27.65 vs 96.7 (so35)-71.4%
HellaSwag: 26.71 vs 95.3 (gpt4)-72%
MMLU: 27.04 vs 88.3 (so35)-69.4%
TruthfulQA: 50.63 vs 59 (gpt4)-14.2%
WinoGrande: 49.64 vs 87.5 (gpt4)-43.3%
LLME Score: 0.16794
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)
Miqu 6B Truthy Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Miqu 6B Truthy |
| Repository 🤗 | https://huggingface.co/vicgalle/Miqu-6B-truthy |
| Model Size | 6b |
| Required VRAM | 11.3 GB |
| Updated | 2026-04-01 |
| Maintainer | vicgalle |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 32764 |
| Model Max Length | 32764 |
| Transformers Version | 4.36.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Miqu 6B Truthy
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yi 6B 200K | 195K / 12.1 GB | 16831 | 172 |
| Yi 6B 200K AEZAKMI V2 | 195K / 12.1 GB | 584 | 1 |
| Yi 6B 200K DPO | 195K / 12.1 GB | 691 | 0 |
| Wukong Yi 6B 200K | 195K / 12.1 GB | 5 | 1 |
| Barcenas 6B 200K | 195K / 12.1 GB | 1848 | 2 |
| Yi 6B 200K Llamafied | 195K / 12.1 GB | 10 | 11 |
| Yi 6B 200K Llama | 195K / 12.1 GB | 4 | 5 |
| Llama 3.2 6B AlgoCode | 128K / 12.7 GB | 23 | 1 |
| Chatglm2 6B Port Llama | 32K / 12.5 GB | 5 | 4 |
| Llama 3 6B V0.1 | 8K / 12.6 GB | 78 | 14 |
Note: green Score (e.g. "73.2") means that the model is better than vicgalle/Miqu-6B-truthy .
Rank the Miqu 6B Truthy 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