What are the hardware requirements for Stablelm 2 1 6B Sft Full?

Stablelm 2 1 6B Sft Full requires approximately 3.3 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Stablelm 2 1 6B Sft Full and how large is it?

Stablelm 2 1 6B Sft Full is developed by nnheui, a model with 6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Stablelm 2 1 6B Sft Full perform on standard benchmarks?

Stablelm 2 1 6B Sft Full has the following published scores: MMLU 36.85. Compare against reference models on this page or on the LLM Explorer leaderboards.

Stablelm 2 1 6B Sft Full by nnheui — VRAM 3.3GB, 4K context

Name: Stablelm 2 1 6B Sft Full
Author: nnheui

Stablelm 2 1 6B Sft Full is an open-source language model by nnheui. Features: 6b LLM, VRAM: 3.3GB, Context: 4K, License: other, LLM Explorer Score: 0.15, Arc: 42, HellaSwag: 69.4, MMLU: 36.9, GSM8K: 12.8.

Alignment-handbook Base model:finetune:stabilitya... Base model:stabilityai/stablel... Conversational Dataset:huggingfaceh4/ultracha... Endpoints compatible Generated from trainer Region:us Safetensors Sft Stablelm Tensorboard Trl

Model Card on HF 🤗: https://huggingface.co/nnheui/stablelm-2-1_6b-sft-full

Stablelm 2 1 6B Sft Full Parameters and Internals

Training Details

Data Sources:

HuggingFaceH4/ultrachat_200k

LLM Name	Stablelm 2 1 6b Sft Full
Repository 🤗	https://huggingface.co/nnheui/stablelm-2-1_6b-sft-full
Base Model(s)	Stablelm 2 1 6b stabilityai/stablelm-2-1_6b
Model Size	6b
Required VRAM	3.3 GB
Updated	2026-05-09
Maintainer	nnheui
Model Type	stablelm
Model Files	3.3 GB 0.0 GB
Model Architecture	StableLmForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the Stablelm 2 1 6B Sft Full 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 Stablelm 2 1 6B Sft Full

Best Alternatives	Context / RAM	Downloads	Likes
Stablelm 2 1 6b	4K / 3.3 GB	6627	196
Stablelm 2 1 6b Chat	4K / 6.6 GB	1945	34
Cot 5k	4K / 3.3 GB	1313	0
StableGPT4 Micro 1.6B	4K / 6.6 GB	81	1
StableLM FineTune GPT4	4K / 6.6 GB	5	1
Parrot 1 6B	4K / 3.3 GB	1	1
Stablelm 2 1 6b	4K / GB	18	2
Stablelm 2 Zephyr 1 6b	4K / GB	11	1
Stablelm 2 Zephyr 1 6b	4K / 3.3 GB	14	1
Stablelm 2 Zephyr 1 6b Q4	4K / GB	14	1

Note: green Score (e.g. "73.2") means that the model is better than nnheui/stablelm-2-1_6b-sft-full.