What are the hardware requirements for DeepScaleR 1.5B 6.5bit?

DeepScaleR 1.5B 6.5bit requires approximately 1.4 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 DeepScaleR 1.5B 6.5bit and how large is it?

DeepScaleR 1.5B 6.5bit is developed by mlx-community, a model with 1.5b 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 DeepScaleR 1.5B 6.5bit?

DeepScaleR 1.5B 6.5bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DeepScaleR 1.5B 6.5bit by mlx-community — VRAM 1.4GB, 128K context

Name: DeepScaleR 1.5B 6.5bit
Author: mlx-community

DeepScaleR 1.5B 6.5bit is an open-source language model by mlx-community. Features: 1.5b LLM, VRAM: 1.4GB, Context: 128K, License: mit, LLM Explorer Score: 0.17.

6-bit Base model:agentica-org/deepsc... Base model:quantized:agentica-... Conversational Dataset:ai-mo/numinamath-cot Dataset:hendrycks/competition ... Dataset:kbsdjames/omni-math Dataset:ruc-aibox/still-3-prev... En Endpoints compatible Mlx Qwen2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepScaleR-1.5B-6.5bit

DeepScaleR 1.5B 6.5bit Parameters and Internals

LLM Name	DeepScaleR 1.5B 6.5bit
Repository 🤗	https://huggingface.co/mlx-community/DeepScaleR-1.5B-6.5bit
Base Model(s)	agentica-org/DeepScaleR-1.5B-Preview agentica-org/DeepScaleR-1.5B-Preview
Model Size	1.5b
Required VRAM	1.4 GB
Updated	2026-07-04
Maintainer	mlx-community
Model Type	qwen2
Model Files	1.4 GB
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.47.1
Tokenizer Class	LlamaTokenizer
Padding Token	<｜end▁of▁sentence｜>
Vocabulary Size	151936
Torch Data Type	float32

Rank the DeepScaleR 1.5B 6.5bit 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 DeepScaleR 1.5B 6.5bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 1.5B 1.3M Stretched	1280K / 3.1 GB	11	0
ReaderLM V2	500K / 3.1 GB	35356	804
Reader Lm 1.5B	250K / 3.1 GB	385	608
DeepSeek R1 Distill Qwen 1.5B	128K / 3.5 GB	600051	1545
Ko R1 1.5B Preview	128K / 7.1 GB	8	9
Qwen2.5 1.5B	128K / 3.1 GB	863295	203
VibeThinker 1.5B	128K / 3.5 GB	3417	552
Merge Cord V1	128K / 3.1 GB	155	1
...FT Tulu3 Decontaminated Masked	128K / 3.1 GB	167	0
Qwen2 1.5B	128K / 3.1 GB	195380	102

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/DeepScaleR-1.5B-6.5bit.