What are the hardware requirements for Tiel Coder 35B A3B MLX OQ4e?

Tiel Coder 35B A3B MLX OQ4e requires approximately 21 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Tiel Coder 35B A3B MLX OQ4e and how large is it?

Tiel Coder 35B A3B MLX OQ4e is developed by peculiar-ragdoll, a model with 35b 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 Tiel Coder 35B A3B MLX OQ4e?

Tiel Coder 35B A3B MLX OQ4e is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tiel Coder 35B A3B MLX OQ4e by peculiar-ragdoll — VRAM 21GB

Name: Tiel Coder 35B A3B MLX OQ4e
Author: peculiar-ragdoll

Tiel Coder 35B A3B MLX OQ4e is an open-source language model by peculiar-ragdoll. Features: 35b LLM, VRAM: 21GB, License: mit, Code Generating, LLM Explorer Score: 0.36.

4-bit Agentic-coding Apple-silicon Base model:ornith-ai/ornith-1.... Base model:quantized:ornith-ai... Codegen Conversational En Image-text-to-text Imatrix Mlx Moe Omlx Oq Qwen35moe Qwen3 5 moe Region:us Safetensors Sharded Tensorflow Token-efficient Unsloth-dynamic Vision Zh

Model Card on HF 🤗: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-MLX-oQ4e

Tiel Coder 35B A3B MLX OQ4e Parameters and Internals

LLM Name	Tiel Coder 35B A3B MLX OQ4e
Repository 🤗	https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-MLX-oQ4e
Base Model(s)	ornith-ai/Ornith-1.5-35B-A3B ornith-ai/Ornith-1.5-35B-A3B
Model Size	35b
Required VRAM	21 GB
Updated	2026-08-26
Maintainer	peculiar-ragdoll
Model Type	qwen3_5_moe
Model Files	5.1 GB: 1-of-5 5.1 GB: 2-of-5 5.1 GB: 3-of-5 5.1 GB: 4-of-5 0.6 GB: 5-of-5
Supported Languages	en zh
Generates Code	Yes
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	mit
Model Max Length	262144
Transformers Version	5.8.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Tiel Coder 35B A3B MLX OQ4e 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 Tiel Coder 35B A3B MLX OQ4e

Best Alternatives	Context / RAM	Downloads	Likes
KAT Coder V2.5 Dev	0K / 69.7 GB	17885	537
Qwopus KAT Coder 35B Merged	0K / 137 GB	274	1
KAT Coder V2.5 Dev VL OQ8e Mtp	0K / 38.4 GB	298	2
KAT Coder V2.5 Dev OQ6e	0K / 28.5 GB	142	1
KAT Coder V2.5 Dev VL OQ4e Mtp	0K / 21.5 GB	149	1
KAT Coder V2.5 Dev VL OQ6e Mtp	0K / 30.2 GB	51	3
Qwopus3.6 35B A3B Coder Bf16	0K / 69.9 GB	227	1
Qwopus3.6 35B A3B Coder 8bit	0K / 37.8 GB	740	4
Qwopus3.6 35B A3B Coder 4bit	0K / 20.5 GB	686	3
...der V2.5 Dev Vision OptiQ 4bit	0K / 22.9 GB	93	2

Note: green Score (e.g. "73.2") means that the model is better than peculiar-ragdoll/Tiel-Coder-35B-A3B-MLX-oQ4e.