What are the hardware requirements for Q1 3B PRIME?

Q1 3B PRIME requires approximately 13.6 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Q1 3B PRIME and how large is it?

Q1 3B PRIME is developed by rawsh, a model with 3b 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 Q1 3B PRIME?

Q1 3B PRIME is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Q1 3B PRIME by rawsh — VRAM 13.6GB, 32K context

Name: Q1 3B PRIME
Author: rawsh

Q1 3B PRIME is an open-source language model by rawsh. Features: 3b LLM, VRAM: 13.6GB, Context: 32K, Quantized, LLM Explorer Score: 0.16.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins... Conversational Dataset:prime-rl/eurus-2-rl-da... En Q1 Quantized Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/rawsh/q1-3B-PRIME

Q1 3B PRIME Parameters and Internals

LLM Name	Q1 3B PRIME
Repository 🤗	https://huggingface.co/rawsh/q1-3B-PRIME
Base Model(s)	Qwen/Qwen2.5-3B-Instruct SmallThinker 3B Preview Qwen/Qwen2.5-3B-Instruct PowerInfer/SmallThinker-3B-Preview
Model Size	3b
Required VRAM	13.6 GB
Updated	2026-08-03
Maintainer	rawsh
Model Type	qwen2
Model Files	5.0 GB: 1-of-3 4.9 GB: 2-of-3 3.7 GB: 3-of-3
Supported Languages	en
Quantization Type	q1
Model Architecture	Qwen2ForCausalLM
Context Length	32768
Model Max Length	32768
Transformers Version	4.48.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	float32
Errors	replace

Rank the Q1 3B PRIME 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 Q1 3B PRIME

Best Alternatives	Context / RAM	Downloads	Likes
VibeThinker 3B 8bit	128K / 3.3 GB	740	3
VibeThinker 3B OptiQ 4bit	128K / 2.3 GB	215	2
Qwen Manim Animation 16bit	32K / 6.2 GB	497	0
Qwen2.5 3B Legal Id Sft	32K / 6.2 GB	324	0
Qwen2.5 3B Legal Sft	32K / 6.2 GB	269	0
Akmal Legal Model Sft	32K / 6.2 GB	147	0
Legal Model Sft	32K / 6.2 GB	135	0
...5 3B Skilled Legal Chatbot Sft	32K / 6.2 GB	140	0
...5 3B Instruct Indonesian QLoRA	32K / 6.2 GB	151	0
...sa Assyifa Putri Legal Chatbot	32K / 6.2 GB	208	0

Note: green Score (e.g. "73.2") means that the model is better than rawsh/q1-3B-PRIME.