Quyen V0.1 is an open-source language model by vilm. Features: 4b LLM, VRAM: 7.9GB, Context: 32K, License: other, HF Score: 56, LLM Explorer Score: 0.15, Arc: 48.2, HellaSwag: 72.5, MMLU: 52.9, TruthfulQA: 51.5, WinoGrande: 65.1, GSM8K: 45.9.
Conversational Dataset:argilla/distilabel-cap... Dataset:intel/orca dpo pairs Dataset:ldjnr/capybara Dataset:teknium/openhermes-2.5 En Endpoints compatible Pytorch Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/vilm/Quyen-v0.1
Quyen V0.1 Benchmarks
ARC: 48.21 vs 96.7 (so35)-50.1%
HellaSwag: 72.49 vs 95.3 (gpt4)-23.9%
MMLU: 52.88 vs 88.3 (so35)-40.1%
TruthfulQA: 51.53 vs 59 (gpt4)-12.7%
WinoGrande: 65.11 vs 87.5 (gpt4)-25.6%
GSM8K: 45.87 vs 96.4 (so35)-52.4%
LLME Score: 0.14553
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)
Quyen V0.1 Parameters and Internals
| Model Type |
| |||
| Training Details |
|
| LLM Name | Quyen V0.1 |
| Repository 🤗 | https://huggingface.co/vilm/Quyen-v0.1 |
| Model Size | 4b |
| Required VRAM | 7.9 GB |
| Updated | 2026-03-29 |
| Maintainer | vilm |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Quyen V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen1.5 4B Chat | 32K / 7.9 GB | 10795 | 43 |
| Qwarkstar 4B Instruct Preview | 32K / 9 GB | 8 | 2 |
| Qwen1.5 4B | 32K / 7.9 GB | 11420 | 36 |
| Qwarkstar 4B | 32K / 9 GB | 5 | 0 |
| Qwarkstar 4B Instruct | 32K / 9 GB | 30 | 1 |
| Sailor 4B | 32K / 7.9 GB | 247 | 6 |
| Nusantara 4B Indo Chat | 32K / 7.9 GB | 124 | 2 |
| Sailor 4B Chat | 32K / 7.9 GB | 160 | 2 |
| Reyna CoT 4B V0.1 | 32K / 7.9 GB | 93 | 6 |
| Blossom V5 4B | 32K / 7.9 GB | 95 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than vilm/Quyen-v0.1 .
Rank the Quyen V0.1 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