Qwen2.5-Coder-1.5B-Instruct-mlx-fp16

Model overview

Hellomaniamcoollol publishes Qwen2.5-Coder-1.5B-Instruct-mlx-fp16 as a text-generation model. Captured config identifies Qwen2ForCausalLM with a qwen2 model type, and Safetensors metadata reports 1,543,714,304 parameters. Card data records apache-2.0. Hub tags include mlx, mlx-my-repo, code, codeqwen, and Qwen/Qwen2.5-Coder-1.5B-Instruct as base model and finetune.

Recorded capabilities

Use cases in the source record

• mlx-lm generate workflows following the card's load and generate example.
• Chat-template text generation as shown in the card's apply_chat_template snippet.

Limitations and unknowns

• No evaluation scores were extracted from this record.
• No independent precision or quantization details were extracted beyond the publisher MLX conversion claim and mlx hub tags. Filename tokens are not treated as evidence of fp16 precision.
• Provider state is historical snapshot data, not independently refreshed current availability.
• The MLX conversion source, mlx-lm version, and usage snippets come from the publisher model card and have not been independently verified by Ethen.

Source and provenance

Source: Hellomaniamcoollol/Qwen2.5-Coder-1.5B-Instruct-mlx-fp16

Captured: Unknown. Processed: 2026-09-07T19:35:39.780519+00:00.

Hellomaniamcoollol/Qwen2.5-Coder-1.5B-Instruct-mlx-fp16 The Model Hellomaniamcoollol/Qwen2.5-Coder-1.5B-Instruct-mlx-fp16 was converted to MLX format from Qwen/Qwen2.5-Coder-1.5B-Instruct using mlx-lm version 0.26.4 . Use with mlx pip install mlx-lm from mlx_lm import load, generate model, tokenizer = load( "Hellomaniamcoollol/Qwen2.5-Coder-1.5B-Instruct-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= False , add_generation_prompt= True ) response = gene…