What are the hardware requirements for PaCoRe 8B?

PaCoRe 8B requires approximately 1.2 GB of VRAM and supports a context window of 320K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed PaCoRe 8B and how large is it?

PaCoRe 8B is developed by stepfun-ai, a model with 8b 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 PaCoRe 8B?

PaCoRe 8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

PaCoRe 8B by stepfun-ai — VRAM 1.2GB, 320K context

Name: PaCoRe 8B
Author: stepfun-ai

PaCoRe 8B is an open-source language model by stepfun-ai. Features: 8b LLM, VRAM: 1.2GB, Context: 320K, License: mit, LLM Explorer Score: 0.22.

Arxiv:2601.05593 Conversational Endpoints compatible Qwen3 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/stepfun-ai/PaCoRe-8B

PaCoRe 8B Parameters and Internals

LLM Name	PaCoRe 8B
Repository 🤗	https://huggingface.co/stepfun-ai/PaCoRe-8B
Model Size	8b
Required VRAM	1.2 GB
Updated	2026-08-08
Maintainer	stepfun-ai
Model Type	qwen3
Model Files	3.1 GB 4.2 GB 4.2 GB 3.6 GB 1.2 GB
Model Architecture	Qwen3ForCausalLM
License	mit
Context Length	327680
Model Max Length	327680
Transformers Version	4.51.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the PaCoRe 8B 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 PaCoRe 8B

Best Alternatives	Context / RAM	Downloads	Likes
RLVR 8B 0926	320K / 1.2 GB	63	8
...n3 8B 320K Context 10X Massive	320K / 16.4 GB	20	0
...r Of Horror Jan V1 256K Ctx 8B	256K / 16.1 GB	33	3
... BIG Jan Horror V1 256K Ctx 8B	256K / 16.1 GB	44	0
Qwen3 8B 256K Context 8X Grand	256K / 16.4 GB	95	0
...wen3 8B 192K Context 6X Larger	192K / 16.4 GB	55	0
DeepSeek R1 0528 Qwen3 8B	128K / 16.4 GB	1762293	1082
Marco DeepResearch 8B	128K / 16.3 GB	520	27
Marco DeepResearch 8B	128K / 16.3 GB	242	34
Finch 8B	128K / 16.4 GB	92	3

Note: green Score (e.g. "73.2") means that the model is better than stepfun-ai/PaCoRe-8B.