What are the hardware requirements for Tinyllama Coder Py V12?

Tinyllama Coder Py V12 requires approximately 0.7 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Tinyllama Coder Py V12 and how large is it?

Tinyllama Coder Py V12 is developed by Ramikan-BR, a model with 1.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Tinyllama Coder Py V12 perform on standard benchmarks?

Tinyllama Coder Py V12 has the following published scores: MMLU 26.31. Compare against reference models on this page or on the LLM Explorer leaderboards.

Tinyllama Coder Py V12 by Ramikan-BR — VRAM 0.7GB, 4K context

Name: Tinyllama Coder Py V12
Author: Ramikan-BR

Tinyllama Coder Py V12 is an open-source language model by Ramikan-BR. Features: 1.1b LLM, VRAM: 0.7GB, Context: 4K, License: apache-2.0, Quantized, Code Generating, LLM Explorer Score: 0.17, Arc: 32, HellaSwag: 53.6, MMLU: 26.3, GSM8K: 1.4.

4bit Base model:quantized:unsloth/t... Base model:unsloth/tinyllama-c... Codegen Conversational Dataset:open-llm-leaderboard/d... En Endpoints compatible Gguf Llama Pytorch Quantized Region:us Safetensors Sft Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/Ramikan-BR/tinyllama-coder-py-v12

Tinyllama Coder Py V12 Parameters and Internals

Model Type

text-generation-inference

Additional Notes

The model achieved a benchmark average score of 35.22 across various tasks.

Training Details

Data Sources:

open-llm-leaderboard/details_Ramikan-BR__tinyllama-coder-py-v12

Methodology:

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

LLM Name	Tinyllama Coder Py V12
Repository 🤗	https://huggingface.co/Ramikan-BR/tinyllama-coder-py-v12
Base Model(s)	Tinyllama Chat Bnb 4bit unsloth/tinyllama-chat-bnb-4bit
Model Size	1.1b
Required VRAM	0.7 GB
Updated	2026-07-08
Maintainer	Ramikan-BR
Model Type	llama
Model Files	2.2 GB 2.2 GB 2.2 GB 0.7 GB 1.2 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf\|4bit
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.41.0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Tinyllama Coder Py V12 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 Tinyllama Coder Py V12

Best Alternatives	Context / RAM	Downloads
Tinyllama Coder Py V13	4K / 0.7 GB	203
Tinyllama Coder Py 4bit V3	4K / 1.2 GB	32
Tinyllama Coder Py 4bit V4	4K / 1.2 GB	17
...llama PY CODER 4bit Lora 4k V5	4K / 0.7 GB	24
Tinyllama Coder Py 4bit V10	4K / 0.7 GB	65
Tinyllama Coder Py V20	4K / 0.7 GB	155
Tinyllama Coder Py V18	4K / 0.7 GB	190
Tinyllama Coder Py V19	4K / 0.7 GB	102
Tinyllama Coder Py V21	4K / 0.7 GB	64
Tinyllama Coder Py V23	4K / 2.2 GB	9

Note: green Score (e.g. "73.2") means that the model is better than Ramikan-BR/tinyllama-coder-py-v12.