What are the hardware requirements for Tiny Pickle V3 Coder?

Tiny Pickle V3 Coder requires approximately 61.2 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Tiny Pickle V3 Coder and how large is it?

Tiny Pickle V3 Coder is developed by vsan, a model with 30b 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 Tiny Pickle V3 Coder?

Tiny Pickle V3 Coder is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tiny Pickle V3 Coder by vsan — VRAM 61.2GB, 256K context

Name: Tiny Pickle V3 Coder
Author: vsan

Tiny Pickle V3 Coder is an open-source language model by vsan. Features: 30b LLM, VRAM: 61.2GB, Context: 256K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.25.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-coder-30... Codegen Coding Conversational Endpoints compatible Instruct Moe Qwen3-coder Qwen3 moe Region:us Safetensors Sharded Software-engineering Tensorflow Tiny-pickle

Model Card on HF 🤗: https://huggingface.co/vsan/tiny-pickle-v3-coder

Tiny Pickle V3 Coder Parameters and Internals

LLM Name	Tiny Pickle V3 Coder
Repository 🤗	https://huggingface.co/vsan/tiny-pickle-v3-coder
Base Model(s)	Qwen3 Coder 30B A3B Instruct Qwen/Qwen3-Coder-30B-A3B-Instruct
Model Size	30b
Required VRAM	61.2 GB
Updated	2026-08-10
Maintainer	vsan
Model Type	qwen3_moe
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-13 5.0 GB: 2-of-13 5.0 GB: 3-of-13 5.0 GB: 4-of-13 5.0 GB: 5-of-13 5.0 GB: 6-of-13 5.0 GB: 7-of-13 5.0 GB: 8-of-13 5.0 GB: 9-of-13 5.0 GB: 10-of-13 5.0 GB: 11-of-13 5.0 GB: 12-of-13 1.2 GB: 13-of-13
Generates Code	Yes
Model Architecture	Qwen3MoeForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.14.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Tiny Pickle V3 Coder 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

Quantized Models of the Tiny Pickle V3 Coder

Model	Likes	Downloads	VRAM
Tiny Pickle V3 Coder 4bit	1	95	17 GB

Best Alternatives to Tiny Pickle V3 Coder

Best Alternatives	Context / RAM	Downloads	Likes
...LL MASTER CODER M 1million Ctx	1024K / 84.8 GB	212	11
Qwen3 30B A3B YOYO V3	986K / 61.1 GB	11	7
...07 YOYO2 TOTAL RECALL Instruct	986K / 84.8 GB	27	1
...07 YOYO2 TOTAL RECALL Instruct	986K / 106 GB	20	0
Qwen3 30B A3B YOYO V2	986K / 61.1 GB	19	4
Qwen3 Coder 30B A3B Instruct	256K / 61.1 GB	1746771	1168
...en3 Coder 30B A3B Instruct FP8	256K / 31.2 GB	1556690	191
Qwen3 Coder 30B A3B Instruct	256K / 61.1 GB	9034	27
Qwen3 Coder REAP 25B A3B	256K / 49.8 GB	579	88
Qwen3 30B A3B YOYO V6	256K / 61.1 GB	19	7

Note: green Score (e.g. "73.2") means that the model is better than vsan/tiny-pickle-v3-coder.