MLX conversion for mlx-lm
According to the model card, the weights were converted to MLX format with mlx-lm 0.29.1 and load through the documented mlx_lm load and generate calls after pip install mlx-lm.
Open Source Model Profile · isetnefret
DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16
DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16 is an 8.03B-parameter Llama MLX conversion from isetnefret with a documented mlx-lm loading workflow.
- Publisher
- isetnefret
- Task
- text-generation
- Model type
- llama
- License
- llama3.1
- Library
- mlx
- Publication status
- Accepted · not indexed
Model overview
DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16 is published by isetnefret as an MLX-format Llama text-generation model. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 8,030,261,248 parameters. According to the model card, it converts aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored with mlx-lm 0.29.1, and card data records llama3.1 licensing.
Recorded capabilities
DarkIdol 1.3 lineage
According to the model card, the source is aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored, and hub tags record roleplay, llama3, and sillytavern associations.
Documented generate snippet
According to the model card, the usage snippet covers loading the repository id, applying an available chat template, and calling generate with verbose output.
Use cases in the source record
- MLX text generation using the documented mlx-lm load and generate workflow.
- Conversational and roleplay-style workflows consistent with the record's conversational, roleplay, and sillytavern tags.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: isetnefret/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16
Captured: Unknown. Processed: 2026-09-07T19:35:57.011751+00:00.
isetnefret/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16 The Model isetnefret/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16 was converted to MLX format from aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored using mlx-lm version 0.29.1 . Use with mlx pip install mlx-lm from mlx_lm import load, generate model, tokenizer = load( "isetnefret/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16" ) prompt= "hello" if hasattr (tokenizer, "apply_chat_template" ) and tokenizer.chat_template is not None : messages = [{ "role" : "user" , "content" : prompt}] prompt = tokenizer.apply_chat_template( messages, tokenize…
F001F002F003F004F005F006F007F008F009F010F011F012F013F014F015