What are the hardware requirements for Model?

Model requires approximately 3.5 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 Model and how large is it?

Model is developed by Martingkc, 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 Model?

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

Model by Martingkc — VRAM 3.5GB, 128K context

Name: Model
Author: Martingkc

Model is an open-source language model by Martingkc. Features: 1.5b LLM, VRAM: 3.5GB, Context: 128K, Quantized, LLM Explorer Score: 0.17.

Arxiv:1910.09700 4bit Conversational Endpoints compatible Pytorch Quantized Qwen2 Region:us Safetensors Sft Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/Martingkc/model

Model Parameters and Internals

LLM Name	Model
Repository 🤗	https://huggingface.co/Martingkc/model
Model Size	1.5b
Required VRAM	3.5 GB
Updated	2026-08-03
Maintainer	Martingkc
Model Type	qwen2
Model Files	3.5 GB 3.5 GB
Quantization Type	4bit
Model Architecture	Qwen2ForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.48.3
Tokenizer Class	LlamaTokenizer
Padding Token	<\|vision_pad\|>
Vocabulary Size	151936
Torch Data Type	float16

Rank the Model 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 Model

Best Alternatives	Context / RAM	Downloads	Likes
VibeThinker 1.5B Mlx 4bit	128K / 0.9 GB	1055	26
...ill Qwen 1.5B Unsloth Bnb 4bit	128K / 1.8 GB	11066	16
Eval Model	128K / 7.1 GB	9	1
DeepSeek R1 ForumNXT	128K / 3.5 GB	8	0
Research PathfinderAI	128K / 3.5 GB	19	0
...en 1.5B Trained Alvin0616 Fork	128K / 3.5 GB	14	0
... R1 Distill Qwen 1.5B Bnb 4bit	128K / 1.6 GB	2008	11
...pSeek R1 Distill Qwen 1.5B 500	128K / 1.7 GB	6	0
Umbr0x 1.5B V3.1 16bit 2	128K / 15.2 GB	19	0
Qwen2 1.5B SFT 16bit Alpha	128K / 3.1 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than Martingkc/model.