Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... De En Endpoints compatible Es Facebook Fr Hi It Llama Llama-3 Meta Mlx Pt Pytorch Q8 Quantized Region:us Safetensors Th
Model Card on HF 🤗: https://huggingface.co/jbeiroa/mlx_llama-3.2-1b-q8
Mlx Llama 3.2 1B Q8 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)
Mlx Llama 3.2 1B Q8 Parameters and Internals
| LLM Name | Mlx Llama 3.2 1B Q8 |
| Repository 🤗 | https://huggingface.co/jbeiroa/mlx_llama-3.2-1b-q8 |
| Base Model(s) | |
| Model Size | 1b |
| Required VRAM | 2.5 GB |
| Updated | 2025-03-12 |
| Maintainer | jbeiroa |
| Model Type | llama |
| Model Files | |
| Supported Languages | en de fr it pt hi es th |
| Quantization Type | q8 |
| Model Architecture | LlamaForCausalLM |
| License | llama3.2 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.45.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mlx Llama 3.2 1B Q8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...2 1B Instruct Unsloth Bnb 4bit | 128K / 1.1 GB | 28385 | 3 |
| Llama 3.2 1B Unsloth Bnb 4bit | 128K / 1.1 GB | 11108 | 2 |
| Llama 3.2 1B Instruct Bnb 4bit | 128K / 1 GB | 29837 | 17 |
| ...truct Gptqmodel 4bit Vortex V1 | 128K / 1.6 GB | 1231 | 2 |
| Llama 3.2 1B Instruct 4bit | 128K / 0.7 GB | 23221 | 15 |
| Llama 3.2 1B Bnb 4bit | 128K / 1 GB | 20630 | 15 |
| Llama 3.2 1B Instruct Chat Sft | 128K / 2.5 GB | 6 | 0 |
| Orca Mini V9 5 1B Instruct | 128K / 2.5 GB | 7 | 4 |
| Llama Deepsync 1B | 128K / 2.5 GB | 2 | 3 |
| ... Mini V9 5 1B Instruct Preview | 128K / 2.5 GB | 8 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than jbeiroa/mlx_llama-3.2-1b-q8 .
Rank the Mlx Llama 3.2 1B Q8 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124