What are the hardware requirements for CodeSaka 7.6B?

CodeSaka 7.6B requires approximately 15.2 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 CodeSaka 7.6B and how large is it?

CodeSaka 7.6B is developed by Sakalti, a model with 7b 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 CodeSaka 7.6B?

CodeSaka 7.6B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

CodeSaka 7.6B by Sakalti — VRAM 15.2GB, 32K context

Name: CodeSaka 7.6B
Author: Sakalti

CodeSaka 7.6B is an open-source language model by Sakalti. Features: 7b LLM, VRAM: 15.2GB, Context: 32K, Code Generating, Merged, LLM Explorer Score: 0.16.

Merged Model Arxiv:2306.01708 Base model:qwen/qwen2.5-coder-... Base model:sousiomine/kuroiso-... Base model:suayptalha/homercre... Codegen Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Sakalti/CodeSaka-7.6B

CodeSaka 7.6B Parameters and Internals

LLM Name	CodeSaka 7.6B
Repository 🤗	https://huggingface.co/Sakalti/CodeSaka-7.6B
Base Model(s)	Qwen/Qwen2.5-Coder-7B-Instruct Kuroiso CR 7B 20250124 HomerCreativeAnvita Mix Qw7B Qwen/Qwen2.5-Coder-7B-Instruct SousiOmine/Kuroiso-CR-7B-20250124 suayptalha/HomerCreativeAnvita-Mix-Qw7B
Merged Model	Yes
Model Size	7b
Required VRAM	15.2 GB
Updated	2026-08-01
Maintainer	Sakalti
Model Type	qwen2
Model Files	5.0 GB: 1-of-4 4.9 GB: 2-of-4 5.0 GB: 3-of-4 0.3 GB: 4-of-4
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.48.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|PAD_TOKEN\|>
Vocabulary Size	152064
Torch Data Type	float16
Errors	replace

Rank the CodeSaka 7.6B 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 CodeSaka 7.6B

Best Alternatives	Context / RAM	Downloads	Likes
SakalFusion 7B Beta	986K / 15.2 GB	9	0
Qwen2.5 7B Rebase	986K / 15.2 GB	73	2
Qwen2.5 7B Rebase	986K / 15.2 GB	16	2
...R1 Distill Qwen MFANN Slerp 7B	128K / 15.2 GB	11	0
Qwen2.5 7B Coder Codeio Pp	128K / 15.2 GB	8	5
Qwen2.5 7B CySecButler V0.1	128K / 15.2 GB	9	3
CoT 2.5	128K / 15.2 GB	39	0
Mergekit Ties Uqhfast	128K / 15.2 GB	26	0
CoT 2.5	128K / 15.2 GB	26	0
StockQwen 2.5 7B	128K / 15.2 GB	69	6

Note: green Score (e.g. "73.2") means that the model is better than Sakalti/CodeSaka-7.6B.