LLM EXPLORER 60,645 MODELS INDEXED

Phi 3 Mini 128K Instruct 8bit by mlx-community

By mlx-community · 49 downloads
HF Repo ↗ Copy URL

Phi 3 Mini 128K Instruct 8bit is an open-source language model by mlx-community. Features: 1.1b LLM, VRAM: 4.1GB, Context: 128K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.23, ELO: 1129.

  8bit   Code   Conversational   Custom code   En   Instruct   Mlx   Phi3   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/Phi-3-mini-128k-instruct-8bit 

Phi 3 Mini 128K Instruct 8bit Benchmarks

LMSys ELO 1129 vs 1272 (so35) -11.2%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Phi 3 Mini 128K Instruct 8bit Parameters and Internals

Model Type 
text generation
Additional Notes 
This model was converted to MLX format from the original model "microsoft/Phi-3-mini-128k-instruct".
Supported Languages 
English (Proficient)
LLM NamePhi 3 Mini 128K Instruct 8bit
Repository 🤗https://huggingface.co/mlx-community/Phi-3-mini-128k-instruct-8bit 
Model Size1.1b
Required VRAM4.1 GB
Updated2026-08-01
Maintainermlx-community
Model Typephi3
Instruction-BasedYes
Model Files  4.1 GB
Supported Languagesen
Quantization Type8bit
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3 Mini 128K Instruct 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct 8bit128K / 4.1 GB5977
Phi 3.5 Mini Instruct 8bit128K / 4.1 GB566
Phi3 Gptq 8bits4K / 4.1 GB70