LLM EXPLORER 60,587 MODELS INDEXED

SmolLM2 135M Instruct Q8 Mlx by HuggingFaceTB

By HuggingFaceTB · 198 downloads
HF Repo ↗ Copy URL

SmolLM2 135M Instruct Q8 Mlx is an open-source language model by HuggingFaceTB. Features: 135m LLM, VRAM: 0.1GB, Context: 8K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.16.

  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/SmolLM2-135M-Instruct-Q8-mlx 

SmolLM2 135M Instruct Q8 Mlx Parameters and Internals

LLM NameSmolLM2 135M Instruct Q8 Mlx
Repository 🤗https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct-Q8-mlx 
Base Model(s)  SmolLM2 135M Instruct   HuggingFaceTB/SmolLM2-135M-Instruct
Model Size135m
Required VRAM0.1 GB
Updated2026-07-25
MaintainerHuggingFaceTB
Model Typellama
Instruction-BasedYes
Model Files  0.1 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 135M Instruct Q8 Mlx

Best Alternatives
Context / RAM
Downloads
Likes
...5M Instruct Bnb 4bit Reasoning8K / 0.3 GB141
SmolLM2 135M Instruct Bnb 4bit8K / 0.1 GB6525
SmolLM 135M Instruct 4bit2K / 0.1 GB15386
SmolLM 135M Instruct Fp162K / 0.3 GB322
SmolLM 135M Instruct 8bit2K / 0.1 GB152
Digest Sft38K / 0.1 GB8740
SmolLM2 135M Instruct Heretic8K / 0.1 GB6530
SmolLM2 135M Instruct8K / 0.3 GB1857297388
Digest Sft28K / 0.5 GB1780
SmolLM2 135M Reasoning 5K8K / 0.3 GB2763
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM2-135M-Instruct-Q8-mlx.