What are the hardware requirements for SmolLM2 1.7B Instruct Q8 Mlx?

SmolLM2 1.7B Instruct Q8 Mlx requires approximately 1.8 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SmolLM2 1.7B Instruct Q8 Mlx and how large is it?

SmolLM2 1.7B Instruct Q8 Mlx is developed by HuggingFaceTB, a model with 1.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does SmolLM2 1.7B Instruct Q8 Mlx perform on standard benchmarks?

SmolLM2 1.7B Instruct Q8 Mlx has the following published scores: LMSYS ELO 1062. Compare against reference models on this page or on the LLM Explorer leaderboards.

SmolLM2 1.7B Instruct Q8 Mlx by HuggingFaceTB — VRAM 1.8GB, 8K context

Name: SmolLM2 1.7B Instruct Q8 Mlx
Author: HuggingFaceTB

SmolLM2 1.7B Instruct Q8 Mlx is an open-source language model by HuggingFaceTB. Features: 1.7b LLM, VRAM: 1.8GB, Context: 8K, License: apache-2.0, Quantized, Instruction-Based, ELO: 1062.

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/SmolLM2-1.7B-Instruct-Q8-mlx

SmolLM2 1.7B Instruct Q8 Mlx Benchmarks

LMSys ELO 1062 vs 1272 (so35) -16.5%

^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)

SmolLM2 1.7B Instruct Q8 Mlx Parameters and Internals

LLM Name	SmolLM2 1.7B Instruct Q8 Mlx
Repository 🤗	https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx
Base Model(s)	HuggingFaceTB/SmolLM2-1.7B-Instruct HuggingFaceTB/SmolLM2-1.7B-Instruct
Model Size	1.7b
Required VRAM	1.8 GB
Updated	2026-08-09
Maintainer	HuggingFaceTB
Model Type	llama
Instruction-Based	Yes
Model Files	1.8 GB
Supported Languages	en
Quantization Type	q8
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.42.3
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	49152
Torch Data Type	bfloat16

Rank the SmolLM2 1.7B Instruct Q8 Mlx capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to SmolLM2 1.7B Instruct Q8 Mlx

Best Alternatives	Context / RAM	Downloads	Likes
SmolLM2 1.7B Instruct Bnb 4bit	8K / 1 GB	407	2
SmolLM 1.7B Bnb 4bit	2K / 1 GB	34	2
SmolLM 1.7B Instruct 4bit	2K / 1 GB	70	2
SmolLM 1.7B Instruct 8bit	2K / 1.8 GB	9	1
SmolLM2 1.7B Instruct 16K	16K / 3.4 GB	103	10
SmolLM2 1.7B Instruct	8K / 3.4 GB	154013	742
SmolLM2 1.7B Instruct	8K / 3.4 GB	4909	6
...ygnis Alpha 1.7B V0.1 Instruct	8K / 3.4 GB	11	2
SmolTulu 1.7B Reinforced	8K / 3.4 GB	12	5
SmolLM2 1.7 Persona	8K / 3.5 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM2-1.7B-Instruct-Q8-mlx.