Views
No views yet
1 arc arc/e boolq hswag obkqa piqa wino
2mxfp8 0.665,0.831,0.910,0.790,0.456,0.813,0.772
3
4Quant Perplexity Peak Memory Tokens/sec
5mxfp8 5.073 ± 0.038 34.74 GB 212
6mxfp4 4.950 ± 0.036 21.30 GB 187 arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.647,0.803,0.910,0.773,0.450,0.806,0.742
qx86-hi 0.637,0.798,0.911,0.775,0.442,0.807,0.737System: You are a coding assistant. <|think_off|>
User: What's 2+2?System: You are a coding assistant. <|think_on|>
User: Implement a red-black tree in Rust.preserve_thinking flag:pip install mlx-lm1from mlx_lm import load, generate
2
3model, tokenizer = load("Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-mxfp4-mlx")
4
5prompt = "hello"
6
7if tokenizer.chat_template is not None:
8 messages = [{"role": "user", "content": prompt}]
9 prompt = tokenizer.apply_chat_template(
10 messages, add_generation_prompt=True, return_dict=False,
11 )
12
13response = generate(model, tokenizer, prompt=prompt, verbose=True)