YandexGPT 5 Lite 8B Instruct Q2 is an open-source language model by mlx-community. Features: 8b LLM, VRAM: 2.5GB, Context: 32K, Quantized, Instruction-Based, LLM Explorer Score: 0.24.
2-bit Base model:quantized:yandex/ya... Base model:yandex/yandexgpt-5-... Conversational Instruct Llama Mlx Q2 Quantized Region:us Ru Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/YandexGPT-5-Lite-8B-instruct-q2
YandexGPT 5 Lite 8B Instruct Q2 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)
YandexGPT 5 Lite 8B Instruct Q2 Parameters and Internals
| LLM Name | YandexGPT 5 Lite 8B Instruct Q2 |
| Repository 🤗 | https://huggingface.co/mlx-community/YandexGPT-5-Lite-8B-instruct-q2 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 2.5 GB |
| Updated | 2026-03-28 |
| Maintainer | mlx-community |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ru |
| Quantization Type | q2 |
| Model Architecture | LlamaForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 129024 |
| Torch Data Type | float16 |
Best Alternatives to YandexGPT 5 Lite 8B Instruct Q2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...B Instruct Gradient 1048K 4bit | 1024K / 4.5 GB | 6 | 2 |
| ...B Instruct Gradient 1048K 8bit | 1024K / 8.6 GB | 6 | 1 |
| ...truct Gradient 1048K Bpw6 EXL2 | 1024K / 6.7 GB | 3 | 2 |
| ...truct Gradient 1048K Bpw5 EXL2 | 1024K / 5.8 GB | 6 | 0 |
| Llama 3 8B Instruct 1048K 4bit | 1024K / 4.5 GB | 529 | 25 |
| Llama 3 8B Instruct 1048K 8bit | 1024K / 8.6 GB | 104 | 17 |
| ... Gradient 1048K 8.0bpw H8 EXL2 | 1024K / 8.6 GB | 4 | 3 |
| ...ct Gradient 1048K Bpw2.25 EXL2 | 1024K / 3.4 GB | 0 | 1 |
| Llama 3 8B Instruct 262K 2bit | 256K / 2.5 GB | 7 | 1 |
| ...B Instruct 262k V2 EXL2 5.0bpw | 256K / 5.8 GB | 6 | 1 |
Rank the YandexGPT 5 Lite 8B Instruct Q2 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? 52052 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 v20260327b