What are the hardware requirements for Stellaris Internlm2 20B R512?

Stellaris Internlm2 20B R512 requires approximately 39.8 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 Stellaris Internlm2 20B R512 and how large is it?

Stellaris Internlm2 20B R512 is developed by Weyaxi, a model with 20b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Stellaris Internlm2 20B R512 perform on standard benchmarks?

Stellaris Internlm2 20B R512 has the following published scores: MMLU 66.34. Compare against reference models on this page or on the LLM Explorer leaderboards.

Stellaris Internlm2 20B R512 by Weyaxi — VRAM 39.8GB, 32K context

Name: Stellaris Internlm2 20B R512
Author: Weyaxi

Stellaris Internlm2 20B R512 is an open-source language model by Weyaxi. Features: 20b LLM, VRAM: 39.8GB, Context: 32K, License: other, LLM Explorer Score: 0.13, Arc: 63.8, HellaSwag: 84, MMLU: 66.3, GSM8K: 14.6.

Axolotl Base model:chargoddard/internl... Base model:finetune:chargoddar... Endpoints compatible Generated from trainer Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/Weyaxi/Stellaris-internlm2-20b-r512

Stellaris Internlm2 20B R512 Parameters and Internals

Model Type

LlamaForCausalLM

Additional Notes

Fine-tuned version of the InternLM2-20B-LLama model using the Axolotl framework.

Training Details

Data Sources:

ARB/arb_law.json, ARB/arb_math.json, ARB/arb_mcat_reading.json, ARB/arb_mcat_science.json, ARB/arb_physics.json

Methodology:

Fine-tuned using Axolotl with quantization config from bitsandbytes

Context Length:

4096

LLM Name	Stellaris Internlm2 20B R512
Repository 🤗	https://huggingface.co/Weyaxi/Stellaris-internlm2-20b-r512
Base Model(s)	Internlm2 20B Llama chargoddard/internlm2-20b-llama
Model Size	20b
Required VRAM	39.8 GB
Updated	2026-07-25
Maintainer	Weyaxi
Model Type	llama
Model Files	4.8 GB: 1-of-9 5.0 GB: 2-of-9 5.0 GB: 3-of-9 4.9 GB: 4-of-9 5.0 GB: 5-of-9 5.0 GB: 6-of-9 4.9 GB: 7-of-9 4.1 GB: 8-of-9 1.1 GB: 9-of-9
Model Architecture	LlamaForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Is Biased	0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	92546
Torch Data Type	bfloat16

Rank the Stellaris Internlm2 20B R512 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 Stellaris Internlm2 20B R512

Best Alternatives	Context / RAM	Downloads	Likes
Internlm2 5 20B Llamafied	256K / 39.9 GB	7	5
EAGLE3 GPT Oss 20B	128K / 0.7 GB	507	0
Internlm2 Chat 20B Llama Old	32K / 39.6 GB	8	3
Internlm2 Base 20B Llama	32K / 39.6 GB	6	3
Internlm2 Base 20B Llama	32K / 39.6 GB	6	0
Deita 20B	32K / 39.8 GB	63	1
Internlm2 20B Llama	32K / 39.6 GB	81	20
Bagel 20B V04 Llama	32K / 39.6 GB	6	7
Bagel DPO 20B V04 Llama	32K / 39.6 GB	7	3
Internlm2 Limarp Chat 20B	32K / 39.6 GB	10	3

Note: green Score (e.g. "73.2") means that the model is better than Weyaxi/Stellaris-internlm2-20b-r512.