What are the hardware requirements for Deepseek R1 Qwen32b Mlx 6bit?

Deepseek R1 Qwen32b Mlx 6bit requires approximately 25.5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek R1 Qwen32b Mlx 6bit and how large is it?

Deepseek R1 Qwen32b Mlx 6bit is developed by nisten, a model with 32b 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 Deepseek R1 Qwen32b Mlx 6bit?

Deepseek R1 Qwen32b Mlx 6bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Deepseek R1 Qwen32b Mlx 6bit by nisten — VRAM 25.5GB, 128K context

Name: Deepseek R1 Qwen32b Mlx 6bit
Author: nisten

Deepseek R1 Qwen32b Mlx 6bit is an open-source language model by nisten. Features: 32b LLM, VRAM: 25.5GB, Context: 128K, License: mit, Quantized, Code Generating, LLM Explorer Score: 0.16.

6-bit 6bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-... Code Codegen Conversational Endpoints compatible Quantized Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nisten/deepseek-r1-qwen32b-mlx-6bit

Deepseek R1 Qwen32b Mlx 6bit Parameters and Internals

LLM Name	Deepseek R1 Qwen32b Mlx 6bit
Repository 🤗	https://huggingface.co/nisten/deepseek-r1-qwen32b-mlx-6bit
Base Model(s)	Qwen/Qwen2.5-Coder-32B DeepSeek R1 Distill Qwen 32B Qwen/Qwen2.5-Coder-32B deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Model Size	32b
Required VRAM	25.5 GB
Updated	2026-07-30
Maintainer	nisten
Model Type	qwen2
Model Files	5.3 GB: 1-of-5 5.3 GB: 2-of-5 5.3 GB: 3-of-5 5.3 GB: 4-of-5 4.3 GB: 5-of-5
Quantization Type	6bit
Generates Code	Yes
Model Architecture	Qwen2ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.43.1
Tokenizer Class	LlamaTokenizer
Padding Token	<｜end▁of▁sentence｜>
Vocabulary Size	152064
Torch Data Type	bfloat16

Rank the Deepseek R1 Qwen32b Mlx 6bit 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 Deepseek R1 Qwen32b Mlx 6bit

Best Alternatives	Context / RAM	Downloads	Likes
....5 Coder 32B Instruct Bnb 4bit	32K / 19.2 GB	5519	6
...wen2.5 Coder 32B Instruct 3bit	32K / 14.3 GB	144	4
...wen2.5 Coder 32B Instruct 4bit	32K / 18.5 GB	2357	12
...wen2.5 Coder 32B Instruct 8bit	32K / 34.9 GB	934	14
Qwen2.5 Coder 32B Bnb 4bit	32K / 19.2 GB	550	5
...truct Gptqmodel 4bit Vortex V1	32K / 21.3 GB	83	16
Qwen2.5 Coder 32B 8bit	32K / 34.9 GB	114	4
Qwen2.5 Coder 32B 4bit	32K / 18.5 GB	106	3
...y Qwen2.5coder 32B V24.1q 200K	195K / 65.8 GB	9	2
...2.5 Godzilla Coder V2 51B 128K	128K / 102.1 GB	8	1

Note: green Score (e.g. "73.2") means that the model is better than nisten/deepseek-r1-qwen32b-mlx-6bit.