What are the hardware requirements for Spark X2.5 4B Japanese Pitcher?

Spark X2.5 4B Japanese Pitcher requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Spark X2.5 4B Japanese Pitcher and how large is it?

Spark X2.5 4B Japanese Pitcher is developed by Takenoko12345678, a model with 4b 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 Spark X2.5 4B Japanese Pitcher?

Spark X2.5 4B Japanese Pitcher is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Spark X2.5 4B Japanese Pitcher by Takenoko12345678 — VRAM 0.1GB

Name: Spark X2.5 4B Japanese Pitcher
Author: Takenoko12345678

Spark X2.5 4B Japanese Pitcher is an open-source language model by Takenoko12345678. Features: 4b LLM, VRAM: 0.1GB, License: apache-2.0, LLM Explorer Score: 0.28.

Adapter Base model:adapter:takenoko123... Base model:takenoko12345678/sp... Character Dataset:rikkabotan/cute synthe... Dataset:takenoko12345678/japan... Finetuned Ja Japanese Lora Peft Region:us Roleplay Safetensors Spark2 5

Model Card on HF 🤗: https://huggingface.co/Takenoko12345678/Spark-X2.5-4B-Japanese-Pitcher

Spark X2.5 4B Japanese Pitcher Parameters and Internals

LLM Name	Spark X2.5 4B Japanese Pitcher
Repository 🤗	https://huggingface.co/Takenoko12345678/Spark-X2.5-4B-Japanese-Pitcher
Base Model(s)	Takenoko12345678/Spark-X2.5-4B-Japanese Takenoko12345678/Spark-X2.5-4B-Japanese
Model Size	4b
Required VRAM	0.1 GB
Updated	2026-09-29
Maintainer	Takenoko12345678
Model Files	0.1 GB
Supported Languages	ja
Model Architecture	Adapter
License	apache-2.0
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	gate_proj\|up_proj\|q_k_v_proj\|out_proj\|down_proj\|g_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16

Rank the Spark X2.5 4B Japanese Pitcher 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 Spark X2.5 4B Japanese Pitcher

Best Alternatives	Context / RAM	Downloads	Likes
Qwen Las V0.1	0K / 0 GB	6	0
Visual Jev 4B Answer Sft	0K / 0.1 GB	466	2
Imajev 4B	0K / 0.5 GB	64	3
...ate Field Intelligence Adapter	0K / 0.1 GB	44	1
Text To Sql Shop R1	0K / 0.1 GB	24	0
Norn V15	0K / 0.1 GB	22	1
Paritok 4B V1	0K / 0.3 GB	71	3
MyceLM Qwen3.5 4B LoRA	0K / 0.1 GB	5	0
Qwen Sft Ls V0.1	0K / 0 GB	6	0
Qwen Sft La V0.1	0K / 0 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than Takenoko12345678/Spark-X2.5-4B-Japanese-Pitcher.