The original BF16 weights are 55.6 GB. This quantization reduces that to 20 GB — runnable on any Mac with 32 GB+ unified memory, with full reasoning capability intact.
For smaller Macs, see the 4-bit version (14 GB, 24 GB+ RAM).
Most local LLMs are reactive — they start generating a response before they've fully mapped out the logic. This model is deliberative.
Distilled from Claude 4.6 Opus reasoning trajectories, it enters a <think> state before answering where it deconstructs the problem, traces logic flows, and self-corrects before you see a single word of the final answer.
The practical difference in code review: a standard model looks at self.value -= 1 in a threading context and says "add a lock." This model looks at it and tells you why — that self.value -= 1 compiles to LOAD_FAST → BINARY_SUBTRACT → STORE_FAST, three bytecode ops, and the GIL can release between LOAD and STORE. The explanation matters as much as the fix.
Three hand-crafted challenges requiring multi-step logical deduction — not pattern matching. Each is designed so a shallow read gives a wrong or incomplete answer.
Challenge
Result
Detail
LRU Cache — is it correct?
✅
Correctly concluded the implementation IS correct — traced every operation
Thread-safe counter race condition
✅
Named exact bytecode ops, traced T1–T6 thread interleave, minimal fix
Pricing engine — find 3 bugs
✅ 3/3
Found > vs >= boundary, loyalty threshold, and discount stacking order
Score: 3/3 challenges fully correct.
For comparison: Qwen2.5-Coder-32B-Instruct-6bit (26 GB, trained on 5.5T code tokens) scored 1.5/3 on the same challenges — it found the obvious >= 10 bug but missed the boundary condition and the stacking order, and gave a factually wrong explanation of why the race condition occurs.
# macOS ships with Python 3.9 which is too old — install 3.12 via Homebrew
brew install python@3.12
/opt/homebrew/bin/python3.12 -m venv ~/mlx-venv
~/mlx-venv/bin/pip install mlx-lm
Use apply_chat_template with enable_thinking=True. This is the idiomatic way to trigger reasoning mode — no manual prompt construction needed.
from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler, make_logits_processors
model, tokenizer = load("BeastCode/Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-6bit")
messages = [
{
"role": "system",
"content": (
"You are an expert code reviewer. Analyze the code carefully, "
"thinking through potential edge cases, security vulnerabilities, "
"and logic flows step-by-step before providing your final review."
),
},
{
"role": "user",
"content": "Review this function:\n\n```python\ndef divide(a, b):\n return a / b\n```",
},
]
prompt = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True,
)
response = generate(
model,
tokenizer,
prompt=prompt,
max_tokens=8192, # reasoning models need room — don't go below 4096
sampler=make_sampler(temp=0.7, min_p=0.05),
logits_processors=make_logits_processors(
repetition_penalty=1.15,
repetition_context_size=64,
),
verbose=True,
)
print(response)
Important: Do not set max_tokens below 4096. The <think> block alone consumes 300–800 tokens on a moderately complex question. If the limit is hit before </think> is emitted, the model never transitions to its answer phase and loops indefinitely. Use 4096 for single functions, 8192 for full PR diffs.
Sampling params:repetition_penalty=1.15 is essential for quantized reasoning models. Without it, the model can enter a local probability minimum and repeat the same sentence until the token limit. temp=0.7 + min_p=0.05 prevents greedy decoding.
import re
def strip_thinking(text: str) -> str:
"""Remove the internal reasoning block, returning only the final answer."""
return re.sub(r'<think>.*?</think>\s*', '', text, flags=re.DOTALL).strip()
clean_response = strip_thinking(response)
The 4-bit version is faster and suitable for quick checks. The 6-bit version is the right choice when correctness matters: it found all 3 bugs in every reasoning challenge, including subtle boundary conditions and multi-step logic errors the 4-bit and the larger code-specialist model missed.
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject: 
BAAI