the new Mac Studio and Mac mini start shipping monday. so this week is one question: which machine do I need for the models people are actually running right now.
how I picked the models: what's being downloaded this month on Hugging Face, what's being talked about on Hacker News and LM Studio, and what has an MLX build. not lifetime downloads, not hype with no adoption.
how to read the sizes: every number is the MLX weights on disk, pulled from the actual file list on Hugging Face. a model needs a bit more than that to run, for the KV cache and macOS. so "fits" means loads with room for normal chat. long prompts on the big models get tight. speed numbers I don't have, that's what the replies are for.
1. the new machines
Mac mini M6: 16 GB base, 32 GB max, 170 GB/s, from $899.
Mac mini M5 Pro: up to 64 GB, 307 GB/s, from $1,699.
Mac Studio M5 Max: up to 128 GB, 614 GB/s, from $2,499.
Mac Studio M5 Ultra: up to 512 GB, 1.2 TB/s, from $5,499. the 512 GB config slips to late october.
memory decides what you can run. bandwidth decides how fast. pick memory first.
Apple: Mac Studio
Apple: Mac mini
2. the cheat sheet
grouped by the smallest new Mac that fits. within each tier, most downloaded first.
16 GB. base Mac mini M6.
MiniCPM5 2B (OpenBMB). 1.4 GB. best model under 4B right now, and the publisher ships the MLX build themselves.
MLX
Spark-X2.5 4B. 3.0 GB. 1M context, built for on-device agents.
MLX
Llama 3.1 8B (Meta). 4.5 GB. old, still the most pulled model on Ollama by a mile.
MLX
Gemma 4 E4B (Google). 5.1 GB. the phone-class Gemma, does audio and vision.
MLX
Gemma 4 12B (Google). 6.7 GB. 2.7M downloads this month.
MLX
Ternary Bonsai 2 27B (PrismML). 8.6 GB. a Qwen3.8-27B squeezed to under 9 GB, claiming 98% of the quality. two days old, top of trending, unproven. the card reports about 47 tok/sec on an M5 Max.
MLX
gpt-oss-20b (OpenAI). 11.2 GB. a year old, still 6.7M downloads last month. 3.6B active so it's quick.
MLX
32 GB. Mac mini M6 maxed, or M5 Pro.
Gemma 4 26B-A4B (Google). 15.3 GB. the most downloaded model on this whole list, 9.8M last month. 4B active so it flies. Unsloth has a 3-bit MLX at 13.2 GB.
MLX
Unsloth UD MLX 3-bit
Qwen3.8-27B (Alibaba). 16.1 GB. 7.4M downloads last month, top of the agentic leaderboards, does vision.
MLX
Qwen3-Coder-30B-A3B (Alibaba). 17.2 GB. the coding workhorse. 3B active.
MLX
Gemma 4 31B (Google). 18.4 GB. the dense one. Unsloth MLX at 23.3 GB.
MLX
Unsloth UD MLX 4-bit
Qwen3.6-35B-A3B (Alibaba). 20.4 GB, or 14.9 GB pruned. see section 3.
MLX
pruned
MiniMax H3 (video). 25.3 GB. the Hailuo 3.0 video model, open weights since august, 4.4M downloads last month. 15 second clips with stereo audio. this is a community MLX conversion, and check the license, it reportedly restricts public use in the US, EU and UK.
MLX
128 GB. Mac Studio M5 Max.
gpt-oss-120b (OpenAI). 62.3 GB. 5.2M downloads last month. this alone justifies a Max.
MLX
MiniMax M2 pruned (139B). 73.9 GB. see section 3.
MLX
GLM 4.7 pruned (185B). 98.2 GB. see section 3.
MLX
Tencent Hy3 (295B). 98.8 GB at 2.7 bits. Apache 2. a 295B model inside a Max.
MLX
256 GB. Mac Studio M5 Ultra.
DeepSeek V4 Flash. 160.1 GB. the V4.1 Flash from last week only has a 428 GB mixed build so far, that one needs the 512.
MLX
Kimi K3 (Moonshot). 181.2 GB, pruned to 543B and 2-bit. the biggest open model ever released. see section 3.
MLX
GLM 5.3 Flash (Z.ai). 181.9 GB mixed 4/8-bit. 320B total, 18B active, 2.7M downloads last month.
MLX
MiniMax M3 (428B). 241.5 GB. official mlx-community build.
MLX
512 GB. late october.
GLM 5.3 (Z.ai). 419.4 GB. the strongest open coding model on the benchmarks.
MLX
DeepSeek V4.1 Flash. 427.6 GB mixed. expect a smaller build soon.
MLX
short version: a 32 GB Mac mini runs the five most downloaded models in the world right now. a Max adds gpt-oss-120b and the pruned giants. a 256 Ultra runs everything but the two 400 GB monsters.
3. what you couldn't run last month and can now
some of those sizes only exist because of a pruning trick that showed up on mlx-community in the last few weeks.
REAP, from Cerebras, ICLR 2026. a MoE model has hundreds of experts per layer and most barely get used. REAP ranks each expert by how often the router picks it times how much it changes the output, then deletes the bottom half. then you quantize what's left. the paper claims 96.8% of code quality kept at 25% pruning and 91.4% at 50%, on their test models. nobody has benchmarked the community builds below yet, so treat those as the paper's claim, not a promise.
what it changed:
Qwen3.6-35B-A3B: 20.4 GB down to 14.9 GB, with the card reporting 11.6 GB peak. tight to comfortable on a 24 GB Mac.
Kimi K3: 2.78 trillion parameters, no MLX build possible. pruned and 2-bit it's 181 GB on a 256 Ultra.
MiniMax M2 and GLM 4.7: both were Ultra-only. pruned they're 74 and 98 GB, inside a Max.
there's a small tool that does this to any mlx-lm MoE on your own Mac.
reap-mlx on GitHub
4. OptiQ, the other name in those repos
OptiQ is a mixed precision quantizer for MLX. sensitive layers get more bits instead of everything at 4. pip install mlx-optiq.
the part that matters on a small Mac is the KV cache. their post claims a 4-bit KV cache at 32k context runs 34% below fp16 and within 2% of its speed, while stock mlx-lm's 4-bit cache actually uses more than fp16 at that length.
if you're on 24 or 32 GB and running long context, try this first.
OptiQ docs
the KV cache post
5. Unsloth now ships MLX weights
if you grab Unsloth GGUFs out of habit, they now publish native MLX builds, tagged UD for Unsloth Dynamic. Qwen3.6-35B-A3B, Qwen3.6-27B, Gemma 4 31B and 26B-A4B so far. linked above where they exist.
Unsloth on Hugging Face
6. video on a Mac, quick status
MiniMax H3 is the one to try, see the 32 GB tier. Wan 2.2 from last year still runs through mlx-video, but Wan 3.0 launched in august as closed API only after Alibaba pre-announced it as open. Seedance 2.5 is API only. HunyuanVideo 1.5 has an unofficial Mac port and not much else.
mlx-video
7. also this week
mlx-vlm shipped 0.7.0 and 0.7.1: continuous batching, MoE offloading, GLM 5 Next, SAM 3.1 video tracking, DINOv2.
mlx-audio shipped three point releases with streaming speech to text and new TTS models.
mlx-lm has no new tag yet but the last week of commits adds OLMo Hybrid, Spark-X2.5, a Qwen3 Next pipeline, a server memory leak fix on model swap, and a faster detokenizer. expect a release soon.
mlx-vlm releases
mlx-audio releases
mlx-lm commits
that's the week.
if you ordered one of the new machines, which tier did you pick and what's the first model you're loading?
and if you're already running any of these on Apple silicon, post your chip, the model, and tok/sec. I'll fold real numbers back into this post.
Stay Frosty,