Apple M5 Max for local LLMs 14 measured results from 3 builds, each linked to its source.
Memory unified memory: 36–128 GB in our builds Memory bandwidth not listed Typical EU price not tracked yet
All builds with the Apple M5 Max All measured results (MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)
Model Build Ran on Quant Engine tok/s Details Gemma 4 26B-A4B MacBook Pro M5 Max 128 GB: Qwen3.6 35B-A3B at 271 tok/s (mlx-serve + MTP), Gemma 4 26B-A4B at 166 mixed / see build 4-bit MLX (QAT) Rapid-MLX 0.16.1 + DFlash 166 ⚡ spec-decode (DFlash) Qwen3.5 9B Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX mixed / see build 4-bit MLX Rapid-MLX 0.16.1 (MTP) 115.5 ⚡ spec-decode (MTP) Qwen3.5 9B Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX mixed / see build 4-bit MLX oMLX 0.7.0 78.0 Qwen3.6 35B-A3B MacBook Pro M5 Max 128 GB: Qwen3.6 35B-A3B at 271 tok/s (mlx-serve + MTP), Gemma 4 26B-A4B at 166 mixed / see build 4-bit MLX (mlx-serve build) mlx-serve 26.10.2 + MTP 271 ⚡ spec-decode (MTP) Qwen3.6 35B-A3B MacBook Pro M5 Max 128 GB: Qwen3.6 35B-A3B at 271 tok/s (mlx-serve + MTP), Gemma 4 26B-A4B at 166 mixed / see build 4-bit MLX Rapid-MLX 0.16.1 + MTP 240 ⚡ spec-decode (MTP) Qwen3.6 35B-A3B Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX mixed / see build 4-bit MLX Rapid-MLX 0.16.1 (MTP) 173.4 ⚡ spec-decode (MTP) Qwen3.6 35B-A3B Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX mixed / see build 4-bit MLX oMLX 0.7.0 145.8 Qwen3.6 35B-A3B Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX mixed / see build 4-bit MLX LM Studio (MLX) 124.5 Qwen3.6 35B-A3B MacBook Pro M5 Max 128 GB: Qwen3.6 35B-A3B at 271 tok/s (mlx-serve + MTP), Gemma 4 26B-A4B at 166 mixed / see build 4-bit MLX mlx_lm.server 0.32.2 107 Qwen3.8 27B Apple M5 Max (40-core GPU) 128 GB running Qwen3.8 27B with MTP drafter mixed / see build 4-bit MLX + Qwen3.8-27B-MTP-4bit drafter oMLX v0.6.0, MTP enabled 45.3 ⚡ spec-decode (MTP) prefill 963.4 tok/s context: 1K (45.8 tok/s at 4K) 📏 oMLX community benchmark upload, peak memory 19.1 GB Qwen3.8 27B Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX mixed / see build 4-bit MLX Rapid-MLX 0.16.1 (MTP) 37.9 ⚡ spec-decode (MTP) Qwen3.8 27B MacBook Pro M5 Max 128 GB: Qwen3.6 35B-A3B at 271 tok/s (mlx-serve + MTP), Gemma 4 26B-A4B at 166 mixed / see build 4-bit MLX same server, no speculation 31 Qwen3.8 27B Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX mixed / see build 4-bit MLX LM Studio (MLX) 26.0 Qwen3.8 27B Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX mixed / see build 4-bit MLX oMLX 0.7.0 25.3
All Apple M5 Max builds: see also all GPUs · best LLMs by memory size · download the dataset .
FAQ How fast is the Apple M5 Max for local LLMs? The fastest plain-decode result we have is 145.8 tok/s on Qwen3.6 35B-A3B (4-bit MLX, oMLX 0.7.0) in Mac Studio M5 Max 36 GB: Qwen3.6 35B-A3B at 173 tok/s (Rapid-MLX), 146 on oMLX . Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 14 measured results from 3 builds.
How much memory does the Apple M5 Max have? unified memory: 36–128 GB in our builds.
Which models have been measured on the Apple M5 Max? Gemma 4 26B-A4B, Qwen3.5 9B, Qwen3.6 35B-A3B, Qwen3.8 27B.
Where do these numbers come from? Every row links to a build page with its original public source (benchmark logs, READMEs, forum posts). RigBase does not re-run the benchmarks. Results marked ⚡ use speculative decoding and are not comparable 1:1 with plain decode.
Ad · this space is available Sponsor this spot: reach people building local AI rigs. One clearly-labeled slot per page, no tracking scripts. Sponsor this spot → Not enough VRAM? Rent before you buy. Run Apple M5 Max-class models on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+.
Try it on Runpod Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms ). It never affects our data.