Large model fidelity on Mac
When fidelity is the point, exact mode is the proof. Across every measured exact run in this suite, top-1 agree stays at 1.00, from the 80B coding MoE through 229B, 235B, and the 426B-class checkpoint. That is a clean signal that the router-selected experts are the ones that ran.
Speed when you want it
The speed setting is the other knob: more tok/s for a measured fidelity cost, with tool calls and the start of every turn held to a stricter setting. Where the cache has room, speed keeps top-1 agree at 1.00 while running much faster: the 80B coding MoE at 34.9 tok/s (from 13.9 exact) at 32 GB, and the 229B at 19.2 (from 7.88) at 48 GB. The 235B holds 0.98 at 48 GB. On the tightest sandboxes the biggest models drift, and the table shows exactly where, so you pick reliable exact or faster speed with numbers in the open.
Fidelity table
| Model | RAM | Mode | Decode tok/s | Tool call tok/s | First turn s | Task s | Top-1 agree |
|---|---|---|---|---|---|---|---|
| Qwen3-Coder-Next 80B-A3B (6-bit) | 16 GB | speed | 41.2 | 41.8 | 17.4 | 57 | 0.91 |
| Qwen3-Coder-Next 80B-A3B (6-bit) | 16 GB | exact | 6.44 | 6.35 | 17.4 | 129 | 1.00 |
| Qwen3-Coder-Next 80B-A3B (6-bit) | 32 GB | speed | 34.9 | 35.0 | 15.9 | 47 | 1.00 |
| Qwen3-Coder-Next 80B-A3B (6-bit) | 32 GB | exact | 13.9 | 14.8 | 16.1 | 77 | 1.00 |
| Qwen3-Coder-Next 80B-A3B (6-bit) | 48 GB | speed | 34.5 | 34.5 | 15.8 | 44 | 1.00 |
| Qwen3-Coder-Next 80B-A3B (6-bit) | 48 GB | exact | 17.7 | 18.3 | 16.2 | 57 | 1.00 |
| Qwen3.8-Flash-Next 229B (6-bit) | 16 GB | speed | 17.1 | 16.9 | 37.3 | 128 | 0.30 |
| Qwen3.8-Flash-Next 229B (6-bit) | 16 GB | exact | 3.53 | 3.57 | 38.2 | 373 | 1.00 |
| Qwen3.8-Flash-Next 229B (6-bit) | 32 GB | speed | 18.3 | 18.1 | 31.5 | 116 | 1.00 |
| Qwen3.8-Flash-Next 229B (6-bit) | 32 GB | exact | 6.18 | 6.03 | 31.7 | 233 | 1.00 |
| Qwen3.8-Flash-Next 229B (6-bit) | 48 GB | speed | 19.2 | 19.4 | 32.2 | 112 | 1.00 |
| Qwen3.8-Flash-Next 229B (6-bit) | 48 GB | exact | 7.88 | 7.72 | 32.0 | 186 | 1.00 |
| Qwen3-235B-A22B (4-bit) | 16 GB | speed | 3.46 | - | 45.9 | 563 | 0.19 |
| Qwen3-235B-A22B (4-bit) | 16 GB | exact | 1.13 | 1.12 | 46.6 | 605 | 1.00 |
| Qwen3-235B-A22B (4-bit) | 32 GB | speed | 9.71 | 9.71 | 44.6 | 183 | 0.88 |
| Qwen3-235B-A22B (4-bit) | 32 GB | exact | 1.82 | 1.70 | 46.6 | 464 | 1.00 |
| Qwen3-235B-A22B (4-bit) | 48 GB | speed | 9.19 | 9.28 | 42.1 | 149 | 0.98 |
| Qwen3-235B-A22B (4-bit) | 48 GB | exact | 2.62 | 2.38 | 47.6 | 343 | 1.00 |
| MiniMax-M3 426B (4-bit) | 32 GB | speed | 3.53 | 3.38 | 43.7 | 366 | 0.38 |
| MiniMax-M3 426B (4-bit) | 32 GB | exact | 1.41 | 1.39 | 44.7 | 808 | 1.00 |
| MiniMax-M3 426B (4-bit) | 48 GB | speed | 4.62 | 4.47 | 44.9 | 295 | 0.75 |
| MiniMax-M3 426B (4-bit) | 48 GB | exact | 2.20 | 2.18 | 43.1 | 526 | 1.00 |
Source: Global Agent 1.2.0 bench harness on Apple M5 Pro, 2026-10-09. Each model builds the same Express ping/pong app with a web page, installs it and starts it, using the system prompt and tools the app sends. Decode tok/s is the median across the task's requests. Speed is the speed slider at 20; exact keeps every expert the router picks. 16 and 32 GB are sandboxed on the same Mac. MiniMax-M3 needs 32 GB or more. Full interactive tables: globalagent.dev/benchmarks.
Download free for Mac - Read the docs - Licenses
Questions: info@globalagent.dev
© QWERTY Code LLC - Terms - EULA - Get started - Docs