LLM EXPLORER 56,604 MODELS INDEXED

SmolLM2 360M Instruct Q8 Mlx by HuggingFaceTB

By HuggingFaceTB · 93 downloads
HF Repo ↗ Copy URL

SmolLM2 360M Instruct Q8 Mlx is an open-source language model by HuggingFaceTB. Features: 360m LLM, VRAM: 0.4GB, Context: 8K, License: apache-2.0, Quantized, Instruction-Based.

  8-bit Base model:huggingfacetb/smoll... Base model:quantized:huggingfa...   Conversational   En   Endpoints compatible   Instruct   Llama   Mlx   Mlx-my-repo   Onnx   Q8   Quantized   Region:us   Safetensors   Transformers.js
Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct-Q8-mlx 

SmolLM2 360M Instruct Q8 Mlx Parameters and Internals

LLM NameSmolLM2 360M Instruct Q8 Mlx
Repository 🤗https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct-Q8-mlx 
Base Model(s)  SmolLM2 360M Instruct   HuggingFaceTB/SmolLM2-360M-Instruct
Model Size360m
Required VRAM0.4 GB
Updated2026-08-09
MaintainerHuggingFaceTB
Model Typellama
Instruction-BasedYes
Model Files  0.4 GB
Supported Languagesen
Quantization Typeq8
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.42.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to SmolLM2 360M Instruct Q8 Mlx

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 360M Instruct Bnb 4bit8K / 0.3 GB5203
SmolLM2 360M Bnb 4bit8K / 0.3 GB462
SmolLM 360M Instruct 8bit2K / 0.4 GB462
Smol Lm2 360 Instruct8K / 0.7 GB3073
SmolLM2 360M Instruct8K / 0.7 GB476032208
Smollm2 360M Text2sql Sft8K / 1.4 GB1940
Smollm3 720prms8K / 0.7 GB50
ProseFlow V1 360M Instruct8K / 0.7 GB51
SmolLM2 Rethink 360M8K / 1.4 GB131
SolaraV2 Coder 05118K / 0.7 GB131
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM2-360M-Instruct-Q8-mlx.