Qwen3-Next-80B-A3B-Instruct Legacy
Files and memory at 8K context
No verified quantized file for the requested formats.
Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory. Legacy model: sizes on device pages are estimated from parameter count.
Quality
Artificial Analysis Intelligence Index
Unknown
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 10
| Hardware | Quant | Backend | Prompt t/s | Gen t/s | Date | Source |
|---|---|---|---|---|---|---|
| Apple M3 Max (40-core GPU), 128 GB unified memory | MLX 4-bit | MLX | 1,100 | 66 | 2026-07-07 | omlx.ai |
| Apple M3 Ultra (60-core GPU), 96 GB unified memory | MLX 4-bit | MLX | 1,266 | 82.2 | 2026-06-18 | omlx.ai |
| Apple M5 Max (40-core GPU), 128 GB unified memory | MLX 4-bit | MLX | 2,188 | 91.5 | 2026-05-30 | omlx.ai |
| Apple M4 Max (40-core GPU), 128 GB unified memory | MLX 4-bit | MLX | 1,142 | 80.9 | 2026-05-26 | omlx.ai |
| Apple M1 Ultra (48-core GPU), 64 GB unified memory | MLX 4-bit | MLX | 450 | 47.1 | 2026-05-18 | omlx.ai |
| Apple M5 Pro (20-core GPU), 64 GB unified memory | MLX 4-bit | MLX | 1,254 | 73.4 | 2026-05-10 | omlx.ai |
| Apple M4 Pro (20-core GPU), 64 GB unified memory | MLX 4-bit | MLX | 628 | 63.1 | 2026-05-03 | omlx.ai |
| Apple M1 Max (32-core GPU), 64 GB unified memory | MLX 4-bit | MLX | 382 | 47 | 2026-04-10 | omlx.ai |
| Apple M2 Ultra (60-core GPU), 192 GB unified memory | MLX 4-bit | MLX | 597 | 60.6 | 2026-03-13 | omlx.ai |
| Mac Studio M2 Ultra 192GB | MLX 8-bit | MLX | — | 57.8 | 2025-10-09 | mlx-lm #492 |
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database