LLM EXPLORER 59,516 MODELS INDEXED

Llama 3 Smaug 8B 4bit by mlx-community

By mlx-community · 16 downloads
HF Repo ↗ Copy URL

Llama 3 Smaug 8B 4bit is an open-source language model by mlx-community. Features: 8b LLM, VRAM: 5GB, Context: 8K, License: llama2, Quantized, LLM Explorer Score: 0.14, Arc: 59.6, HellaSwag: 80, MMLU: 65.8, GSM8K: 55.9.

  4bit   Autotrain compatible   Conversational   Endpoints compatible   Llama   Mlx   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/Llama-3-Smaug-8B-4bit 

Llama 3 Smaug 8B 4bit Parameters and Internals

LLM NameLlama 3 Smaug 8B 4bit
Repository 🤗https://huggingface.co/mlx-community/Llama-3-Smaug-8B-4bit 
Base Model(s)  Llama 3 Smaug 8B   abacusai/Llama-3-Smaug-8B
Model Size8b
Required VRAM5 GB
Updated2024-08-09
Maintainermlx-community
Model Typellama
Model Files  5.0 GB
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length8192
Model Max Length8192
Transformers Version4.37.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 Smaug 8B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB102
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB111
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB22
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB50
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB52525
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB21317
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB23
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB51
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB111
...B Instruct 262k V2 EXL2 5.0bpw256K / 5.8 GB51
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Llama-3-Smaug-8B-4bit.