What are the hardware requirements for Scal Lite 60B Code?

Scal Lite 60B Code requires approximately 34.8 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Scal Lite 60B Code and how large is it?

Scal Lite 60B Code is developed by Scalai, a model with 120b 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 Scal Lite 60B Code?

Scal Lite 60B Code is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Scal Lite 60B Code by Scalai — VRAM 34.8GB, 128K context

Name: Scal Lite 60B Code
Author: Scalai

Scal Lite 60B Code is an open-source language model by Scalai. Features: 120b LLM, VRAM: 34.8GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.22.

8-bit Base model:openai/gpt-oss-120b Base model:quantized:openai/gp... Code Dataset:huggingfaceh4/codealpa... En Es Gpt oss Math Moe Mxfp4 Pruning Region:us Safetensors Scalai Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/Scalai/scal-lite-60b-code

Scal Lite 60B Code Parameters and Internals

LLM Name	Scal Lite 60B Code
Repository 🤗	https://huggingface.co/Scalai/scal-lite-60b-code
Base Model(s)	GPT Oss 120B openai/gpt-oss-120b
Model Size	120b
Required VRAM	34.8 GB
Updated	2026-07-15
Maintainer	Scalai
Model Type	gpt_oss
Model Files	2.4 GB: 0-of-14 2.1 GB: 1-of-14 2.4 GB: 2-of-14 2.1 GB: 3-of-14 2.4 GB: 4-of-14 2.1 GB: 5-of-14 2.4 GB: 6-of-14 2.1 GB: 7-of-14 2.4 GB: 8-of-14 2.2 GB: 9-of-14 2.4 GB: 10-of-14 2.1 GB: 11-of-14 3.2 GB: 12-of-14 2.4 GB: 13-of-14 2.1 GB: 14-of-14
Supported Languages	en es
Model Architecture	GptOssForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.55.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	201088

Rank the Scal Lite 60B Code 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 Scal Lite 60B Code

Best Alternatives	Context / RAM	Downloads	Likes
GPT Oss 120B	128K / 65.1 GB	4232947	5068
GPT Oss 120B	128K / 65.1 GB	2742	22
BlueBerry 1	128K / 233.5 GB	150	1
BlueBerry 2	128K / 233.5 GB	143	1
BlueBerry 3	128K / 233.5 GB	140	1
GPT Oss 120B Mxfp4 Bf16	128K / 64.8 GB	1653	2
Medical GPT OSS Swallow 120B	128K / 139.8 GB	139	4
GPT Oss Safeguard 120B	128K / 65.1 GB	4032	99
GPT Oss 120B BF16	128K / 142 GB	8192	8
GPT Oss 120B Dequantized	128K / 135.6 GB	16	0

Note: green Score (e.g. "73.2") means that the model is better than Scalai/scal-lite-60b-code.