Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q8_0 unsloth/GLM-5.3-GGUF | 746 GiB | 17 | unknown | over 192 GB GPU | HF files |
| BF16 unsloth/GLM-5.3-GGUF | 1,404 GiB | 33 | unknown | over 192 GB GPU | HF files |
No verified file: Q4_K_M, Q5_K_M, FP16, MLX 4-bit, MLX 8-bit. 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.
Quality
Artificial Analysis Intelligence Index
44.8
Variant: GLM-5.3 (Max) · observed 2026-10-17 · source
Rank #2 of 75 researched 2026 models.
Arena text rating
1,471
95% CI 1466–1477 · 22,543 votes · published 2026-10-15 · dataset
Exact listed model name; hosted reasoning/quantization may differ from local checkpoint.
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 3
| Hardware | Quant | Backend | Prompt t/s | Gen t/s | Date | Source |
|---|---|---|---|---|---|---|
| Apple M3 Ultra (80-core GPU), 512 GB unified memory | 4bit (GLM-5.3-MLX-mixed-4_8bit) | MLX (oMLX server) | 120 | 12.9 | 2026-10-16 | omlx.ai |
| Apple M3 Ultra (80-core GPU), 512 GB unified memory | 4bit (GLM-5.3-MLX-mixed-4_8bit) | MLX (oMLX server) | 194 | 15 | 2026-10-02 | omlx.ai |
| Apple M3 Ultra (80-core GPU), 512 GB unified memory | 4bit (GLM-5.3-MLX-mixed-4_8bit) | MLX (oMLX server) | 193 | 14.9 | 2026-09-20 | omlx.ai |
Reported by the linked sources, not reproduced by LocalFit. All rows in the speed database