Quark 270M Instruct is an open-source language model by ThingAI. Features: 270m LLM, VRAM: 0.6GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.32.
Bilingual Chat Conversational Custom code En English Instruct It Italian Quark Region:us Safetensors Sft Small-language-model Trained-from-scratch
Model Card on HF 🤗: https://huggingface.co/ThingAI/Quark-270m-Instruct
Quark 270M Instruct Benchmarks
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)
Quark 270M Instruct Parameters and Internals
| LLM Name | Quark 270M Instruct |
| Repository 🤗 | https://huggingface.co/ThingAI/Quark-270m-Instruct |
| Model Size | 270m |
| Required VRAM | 0.6 GB |
| Updated | 2026-06-08 |
| Maintainer | ThingAI |
| Model Type | quark |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | it en |
| Model Architecture | QuarkForCausalLM |
| License | apache-2.0 |
| Model Max Length | 2048 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <pad> |
| Vocabulary Size | 65537 |
| Torch Data Type | bfloat16 |
Rank the Quark 270M Instruct 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? 54413 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