What are the hardware requirements for DeepMath R1 Distill Qwen 7B?

DeepMath R1 Distill Qwen 7B requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DeepMath R1 Distill Qwen 7B and how large is it?

DeepMath R1 Distill Qwen 7B is developed by SoFarSoGoodya, a model with 7b 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 DeepMath R1 Distill Qwen 7B?

DeepMath R1 Distill Qwen 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DeepMath R1 Distill Qwen 7B by SoFarSoGoodya — VRAM 0.1GB

Name: DeepMath R1 Distill Qwen 7B
Author: SoFarSoGoodya

DeepMath R1 Distill Qwen 7B is an open-source language model by SoFarSoGoodya. Features: 7b LLM, VRAM: 0.1GB, License: mit, LLM Explorer Score: 0.25.

Adapter Base model:adapter:deepseek-ai... Base model:deepseek-ai/deepsee... Conversational Dataset:ai-mo/numinamath-cot Deepseek-r1 Dpo En Finetuned Llama-factory Lora Math Peft Qwen Reasoning Region:us Safetensors Sft Zh

Model Card on HF 🤗: https://huggingface.co/SoFarSoGoodya/DeepMath-R1-Distill-Qwen-7B

DeepMath R1 Distill Qwen 7B Parameters and Internals

LLM Name	DeepMath R1 Distill Qwen 7B
Repository 🤗	https://huggingface.co/SoFarSoGoodya/DeepMath-R1-Distill-Qwen-7B
Base Model(s)	DeepSeek R1 Distill Qwen 7B deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Model Size	7b
Required VRAM	0.1 GB
Updated	2026-09-04
Maintainer	SoFarSoGoodya
Model Files	0.1 GB
Supported Languages	en zh
Model Architecture	Adapter
License	mit
Model Max Length	16384
Is Biased	none
Tokenizer Class	LlamaTokenizerFast
Padding Token	<｜end▁of▁sentence｜>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	v_proj\|o_proj\|up_proj\|gate_proj\|down_proj\|q_proj\|k_proj
LoRA Alpha	16
LoRA Dropout	0
R Param	8

Rank the DeepMath R1 Distill Qwen 7B 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 DeepMath R1 Distill Qwen 7B

Best Alternatives	Context / RAM	Downloads	Likes
K2 Horizon 7B Uno	0K / 1.4 GB	10105	16
Dart Gui 7B Autosleep Lora	0K / 0 GB	21	1
...Event Narrator Mistral 7B Lora	0K / 0.1 GB	26	1
...x H3 Prompt Rewriter LoRA Omni	0K / 1.3 GB	27	32
Falcon3 7B Persian Lora	0K / 0.2 GB	22	2
Fedquant Mistral 7B Lora	0K / 0 GB	22	1
...wen2.5 7B Grpo Screen 20261012	0K / 0.2 GB	19	1
Personality Interpretation Zh	0K / 0.3 GB	19	0
Pallade Idrico 7B	0K / 0.3 GB	26	1
Qwen2.5 7B Deal Lora	0K / 0.2 GB	12	1

Note: green Score (e.g. "73.2") means that the model is better than SoFarSoGoodya/DeepMath-R1-Distill-Qwen-7B.