@akazwz_: Ready to start using it, Qwen 3.8 27b, now Ollama directly supports Mac's MLX which is very nice.

X AI KOLs Following News

Summary

The user indicates they are ready to use the Qwen 3.8 27b model, now Ollama directly supports Mac's MLX, making it very comfortable to use.

Ready to start using it, Qwen 3.8 27b, now Ollama directly supports Mac's MLX which is very comfortable. https://t.co/yQrYTGS19R
Original Article
View Cached Full Text

Cached at: 08/17/26, 12:13 AM

Getting ready to use qwen3.8 27b — Ollama’s direct MLX support for Mac makes it so smooth to use. https://t.co/yQrYTGS19R

Similar Articles

@nicekate8888: For the past twenty days, I've been obsessing over one thing — how to make Qwen3.6-27B run fast and well on my Mac. I started with Unsloth Q5, got 18 tok/s, and the fan was roaring. Then I switched to MLX 6bit + DFlash, hitting 22 tok/s, still not fast enough. Eventually I found MTPLX 4bit: 43 tok/s with good quality.

X AI KOLs Timeline

The user shares their experience optimizing Qwen3.6-27B inference speed on a Mac using different quantization methods (Unsloth Q5, MLX 6bit + DFlash, MTPLX 4bit), ultimately reaching 43 tok/s.

@cevenif: For those running local LLMs on Macs, here's a tool worth watching — Rapid-MLX. It delivers 2-4x faster inference on M-series chips than Ollama, thanks to being built directly on Apple's MLX framework for more thorough utilization of the chip architecture. Key highlights: KV cache pruning plus…

X AI KOLs Timeline

Rapid-MLX is a local LLM inference tool optimized for Apple M-series chips. Built on the MLX framework, it achieves 2 to 4 times faster inference than Ollama, supports multiple models, tool calling, and an OpenAI API-compatible interface.

@nash_su: Mac inference speed doubled. MTPLX is an integrated solution combining MLX and MTP, specifically optimized for model inference on Apple Silicon. By using models with a custom MTP head, it can deliver doubled inference speed. I tested it with Qwen3.6-27…

X AI KOLs Timeline

MTPLX is an integrated solution combining MLX and MTP, specifically optimized for model inference speed on Apple Silicon. Tests show that Qwen3.6-27B achieves double the inference speed of LM Studio, and it also integrates fan management.

@sanbuphy: K2.6 successfully downloaded and deployed the Qwen3.5-0.8B model locally on a Mac, using the niche Zig language to implement and optimize inference, demonstrating the new model’s generalization ability. After 4,000+ tool calls and 12+ hours of continuous operation, K2.6 iterated 14 times…

X AI KOLs Timeline

K2.6 successfully downloaded and deployed the Qwen3.5-0.8B model locally on a Mac, using the niche Zig language to implement and optimize inference, demonstrating the new model’s generalization ability. After 4,000+ tool calls and 12+ hours of continuous operation, K2.6 iterated 14 times, boosting throughput from ~15 tokens/s to ~193 tokens/s, ultimately achieving 20% faster inference than LM Studio.