What are the hardware requirements for Merge Cord V1?

Merge Cord V1 requires approximately 3.1 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 Merge Cord V1 and how large is it?

Merge Cord V1 is developed by tepirale, a model with 1.5b 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 Merge Cord V1?

Merge Cord V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Merge Cord V1 by tepirale — VRAM 3.1GB, 128K context

Name: Merge Cord V1
Author: tepirale

Merge Cord V1 is an open-source language model by tepirale. Features: 1.5b LLM, VRAM: 3.1GB, Context: 128K, Instruction-Based, Code Generating, Merged, LLM Explorer Score: 0.31.

Merged Model Base model:qwen/qwen2.5-1.5b Base model:qwen/qwen2.5-1.5b-i... Base model:qwen/qwen2.5-coder-... Codegen Conversational Endpoints compatible Instruct Qwen2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/tepirale/merge-cord-v1

Merge Cord V1 Parameters and Internals

LLM Name	Merge Cord V1
Repository 🤗	https://huggingface.co/tepirale/merge-cord-v1
Base Model(s)	Qwen/Qwen2.5-Coder-1.5B-Instruct Qwen/Qwen2.5-1.5B Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-Coder-1.5B-Instruct Qwen/Qwen2.5-1.5B Qwen/Qwen2.5-1.5B-Instruct
Merged Model	Yes
Model Size	1.5b
Required VRAM	3.1 GB
Updated	2026-08-11
Maintainer	tepirale
Model Type	qwen2
Instruction-Based	Yes
Model Files	3.1 GB
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	5.12.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Merge Cord V1 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 Merge Cord V1

Best Alternatives	Context / RAM	Downloads	Likes
Replete Coder Qwen2 1.5B	128K / 3.1 GB	233	23
Qwen2.5 Coder 1.5B Instruct	32K / 3.1 GB	695585	134
Mythos Qwen 1.5B Final	32K / 3.1 GB	104	1
Microcoder 1.5B	32K / 3.1 GB	20	4
Qwen2.5 Coder 1.5B Instruct	32K / 3.1 GB	69796	6
...n2.5 Coder Draft 1.5B Instruct	32K / 3.1 GB	7	0
ProseFlow V1.1.5B Instruct	32K / 3.1 GB	4	1
Arch Agent 1.5B	32K / 3.1 GB	149	9
Hammer2.1 1.5B	32K / 3.1 GB	1933	15
Openhands Lm 1.5B V0.1	32K / 3.1 GB	41	12