What are the hardware requirements for SymboLM 2.1 SmolLM2 1.7B?

SymboLM 2.1 SmolLM2 1.7B requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SymboLM 2.1 SmolLM2 1.7B and how large is it?

SymboLM 2.1 SmolLM2 1.7B is developed by gyawalisanish0, 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 SymboLM 2.1 SmolLM2 1.7B perform on standard benchmarks?

SymboLM 2.1 SmolLM2 1.7B has the following published scores: LMSYS ELO 1062. Compare against reference models on this page or on the LLM Explorer leaderboards.

SymboLM 2.1 SmolLM2 1.7B by gyawalisanish0 — VRAM 0.1GB

Name: SymboLM 2.1 SmolLM2 1.7B
Author: gyawalisanish0

SymboLM 2.1 SmolLM2 1.7B is an open-source language model by gyawalisanish0. Features: 1.7b LLM, VRAM: 0.1GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.41, ELO: 1062.

Adapter Base model:adapter:huggingface... Base model:huggingfacetb/smoll... Conversational Edge-ai En Endpoints compatible Finetuned Gguf Instruct Llama-architecture Lora Peft Q4 Quantized Reasoning Region:us Safetensors Smollm2 Symbolic-ai Token-compression

Model Card on HF 🤗: https://huggingface.co/gyawalisanish0/SymboLM-2.1-SmolLM2-1.7B

SymboLM 2.1 SmolLM2 1.7B 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)

SymboLM 2.1 SmolLM2 1.7B Parameters and Internals

LLM Name	SymboLM 2.1 SmolLM2 1.7B
Repository 🤗	https://huggingface.co/gyawalisanish0/SymboLM-2.1-SmolLM2-1.7B
Base Model(s)	HuggingFaceTB/SmolLM2-1.7B-Instruct HuggingFaceTB/SmolLM2-1.7B-Instruct
Model Size	1.7b
Required VRAM	0.1 GB
Updated	2026-10-20
Maintainer	gyawalisanish0
Instruction-Based	Yes
Model Files	0.1 GB 3.4 GB 1.0 GB 1.8 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf\|q4
Model Architecture	Adapter
License	apache-2.0
Model Max Length	8192
Is Biased	none
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	49152
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	k_proj\|q_proj\|up_proj\|down_proj\|o_proj\|gate_proj\|v_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16
Errors	replace

Rank the SymboLM 2.1 SmolLM2 1.7B 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 SymboLM 2.1 SmolLM2 1.7B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 1.7B Financial Qa Lora	0K / 0 GB	9	1
SmolVLM Instruct DPO	0K / 0.1 GB	17	22