What are the hardware requirements for Sdmkdnks?

Sdmkdnks requires approximately 8 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sdmkdnks and how large is it?

Sdmkdnks is developed by ehristoforu, a model with 4b 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 Sdmkdnks?

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

Sdmkdnks by ehristoforu — VRAM 8GB, 40K context

Name: Sdmkdnks
Author: ehristoforu

Sdmkdnks is an open-source language model by ehristoforu. Features: 4b LLM, VRAM: 8GB, Context: 40K, Merged, LLM Explorer Score: 0.19.

Merged Model Arxiv:2403.19522 Autotrain compatible Base model:apexion-ai/nous-1-4... Base model:dev9124/qwen3-finan... Base model:ertghiu256/qwen3-4b... Base model:huihui-ai/huihui-qw... Base model:mlxha/qwen3-4b-grpo... Base model:polaris-project/pol... Base model:prithivmlmods/draco... Base model:qwen/qwen3-4b Base model:qwen/qwen3-4b-base Base model:vikhrmodels/qvikhr-... Conversational Endpoints compatible Qwen3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ehristoforu/sdmkdnks

Sdmkdnks Parameters and Internals

LLM Name	Sdmkdnks
Repository 🤗	https://huggingface.co/ehristoforu/sdmkdnks
Base Model(s)	Huihui Qwen3 4B Abliterated V2 Draconis Qwen3 Math 4B Preview Polaris 4B Preview Qwen/Qwen3-4B QVikhr 3 4B Instruction Nous 1 4B Qwen3 4B Grpo Medmcqa Qwen3 Finance Model Qwen3 4B Code Reasoning Qwen3 4B Base huihui-ai/Huihui-Qwen3-4B-abliterated-v2 prithivMLmods/Draconis-Qwen3_Math-4B-Preview POLARIS-Project/Polaris-4B-Preview Qwen/Qwen3-4B Vikhrmodels/QVikhr-3-4B-Instruction apexion-ai/Nous-1-4B mlxha/Qwen3-4B-grpo-medmcqa Dev9124/qwen3-finance-model ertghiu256/qwen3-4b-code-reasoning Qwen/Qwen3-4B-Base
Merged Model	Yes
Model Size	4b
Required VRAM	8 GB
Updated	2025-08-09
Maintainer	ehristoforu
Model Type	qwen3
Model Files	5.0 GB: 1-of-2 3.0 GB: 2-of-2
Model Architecture	Qwen3ForCausalLM
Context Length	40960
Model Max Length	40960
Transformers Version	4.54.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Sdmkdnks 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 Sdmkdnks

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 4B Instruct 2507	256K / 8.1 GB	3109972	911
GRPO 4 70	256K / 8.1 GB	11	0
FastContext 1.0 4B SFT	256K / 8.1 GB	5735	357
...2.5 Flash Lite Preview Distill	256K / 8.1 GB	31	1
Lightning 4B	256K / 8.1 GB	13	6
Qwen3 4B Thinking 2507	256K / 8.1 GB	291023	606
Fable Traces	256K / 8.1 GB	347	210
FastContext 1.0 4B RL	256K / 8.1 GB	4559	61
Checkpoint 8000	256K / 8.1 GB	1453	0
Qwen3 4B Instruct 2507 FP8	256K / 5.2 GB	1100744	78

Note: green Score (e.g. "73.2") means that the model is better than ehristoforu/sdmkdnks.