What are the hardware requirements for Smol Llama 220M GQA 32K Theta Sft?

Smol Llama 220M GQA 32K Theta Sft requires approximately 0.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Smol Llama 220M GQA 32K Theta Sft and how large is it?

Smol Llama 220M GQA 32K Theta Sft is developed by Doctor-Shotgun, a model with 220m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Smol Llama 220M GQA 32K Theta Sft?

Smol Llama 220M GQA 32K Theta Sft is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Smol Llama 220M GQA 32K Theta Sft by Doctor-Shotgun — VRAM 0.4GB, 32K context

Name: Smol Llama 220M GQA 32K Theta Sft
Author: Doctor-Shotgun

Smol Llama 220M GQA 32K Theta Sft is an open-source language model by Doctor-Shotgun. Features: 220m LLM, VRAM: 0.4GB, Context: 32K, Instruction-Based, Merged, LLM Explorer Score: 0.1.

Merged Model Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:doctor-shotgun/no-robo... Dataset:jondurbin/airoboros-3.... Dataset:norquinal/claude multi... En Endpoints compatible Instruct Llama Llama 2 Pytorch Region:us Smol llama

Model Card on HF 🤗: https://huggingface.co/Doctor-Shotgun/smol_llama-220M-GQA-32k-theta-sft

Smol Llama 220M GQA 32K Theta Sft Parameters and Internals

Model Type

text generation

Additional Notes

Experimental model meant to serve as a long-context speculative decoding model.

Supported Languages

en (proficient)

Training Details

Data Sources:

cognitivecomputations/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split, cognitivecomputations/Code-74k-ShareGPT-Vicuna, jondurbin/airoboros-3.1, Norquinal/claude_multiround_chat_30k, Doctor-Shotgun/no-robots-sharegpt

Methodology:

finetuning at 32768 context length

Context Length:

32768

Input Output

Input Format:

Alpaca

LLM Name	Smol Llama 220M GQA 32K Theta Sft
Repository 🤗	https://huggingface.co/Doctor-Shotgun/smol_llama-220M-GQA-32k-theta-sft
Merged Model	Yes
Model Size	220m
Required VRAM	0.4 GB
Updated	2026-07-25
Maintainer	Doctor-Shotgun
Model Type	llama
Instruction-Based	Yes
Model Files	0.4 GB
Supported Languages	en
Model Architecture	LlamaForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Smol Llama 220M GQA 32K Theta Sft 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 Smol Llama 220M GQA 32K Theta Sft

Best Alternatives	Context / RAM	Downloads	Likes
Smol Llama 220M Open Instruct	2K / 0.4 GB	6	2

Note: green Score (e.g. "73.2") means that the model is better than Doctor-Shotgun/smol_llama-220M-GQA-32k-theta-sft.