TxemAI/Qwen3-53B-A3B-2507-TOTAL-RECALL-v2-MLX-6bit

Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER — MLX Q6 (6-bit)

MLX 6-bit quantization of DavidAU/Qwen3-53B-A3B-2507-THINKING-TOTAL-RECALL-v2-MASTER-CODER, optimized for Apple Silicon using mlx-lm.

Quantized by TxemAI on an Apple M4 Max (128 GB unified memory).

Q6 is the recommended quant for this model on Apple Silicon. It runs comfortably within 128 GB, delivers near-lossless quality vs Q8, and achieves significantly better throughput due to lower memory pressure.

Benchmark (Apple M4 Max, 128 GB)

Q6 is 48x faster on prompt processing and nearly 2x faster on generation compared to Q8 on this machine, due to the large difference in memory pressure.

About the model

This model is based on Qwen3-30B-A3B-Thinking-2507 (MoE, 128 experts, 10 activated) with the Brainstorm 40x adapter by DavidAU, which expands and recalibrates the reasoning centers of the model to improve depth, coherence, and detail in outputs.

Key characteristics:

• —53B total parameters, ~3.3B activated per token (MoE architecture)
• —256k native context window
• —Thinking mode only — outputs include a <think> reasoning trace before the final response
• —Excels at coding and programming across all major languages
• —Strong performance on reasoning, math, and agentic tasks

For full model details, settings, and recommended samplers, see the original model card.

Usage

pip install mlx-lm

mlx_lm.generate \
  --model TxemAI/Qwen3-53B-A3B-2507-TOTAL-RECALL-v2-MLX-6bit \
  --prompt "Write a Python function to sort a list of dicts by a key" \
  --max-tokens 4096

from mlx_lm import load, generate

model, tokenizer = load("TxemAI/Qwen3-53B-A3B-2507-TOTAL-RECALL-v2-MLX-6bit")

prompt = "Write a Python function to sort a list of dicts by a key"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

response = generate(model, tokenizer, prompt=text, max_tokens=4096, verbose=True)

Recommended inference settings

For complex coding or reasoning tasks, use higher token limits (32k–81k).

Other formats

TxemAI — MLX models for Apple Silicon

This model is part of the TxemAI collection of MLX-quantized models optimized for local inference on Apple Silicon, with a focus on data sovereignty and enterprise use cases.