| Model profile | ||
|---|---|---|
| Model | Size | Approximate size |
| Mistral Large 4Model source: provider1,000,000 tokens max native context | 1050Bactive 49B | 630 GB4-bit quantization |
| Compatible hardware Estimated speeds, not benchmark results: calculated from memory bandwidth and model size. Real results can differ significantly because there is no precise formula for deriving LLM generation speed from hardware specifications alone. | ||||
|---|---|---|---|---|
| Hardware | Memory | Bandwidth | vLLM | Estimated generation |
| DGX H200 | 1128 GBGPU HBM3e | 4800 GB/s | yes | 62 tok/s4-bit quantization |
| DGX Station | 748 GBCoherent Memory | 7100 GB/s | yes | 88 tok/s4-bit quantization |
| ET900N G3 | 748 GBCoherent Memory | 7100 GB/s | yes | 88 tok/s4-bit quantization |
| DGX B200 | 1440 GBGPU HBM3e | 8000 GB/s | yes | 97 tok/s4-bit quantization |
| GB200 NVL72 | 13400 GBGPU HBM3e | 8000 GB/s | yes | 97 tok/s4-bit quantization |
| GB300 NVL72 | 20000 GBGPU HBM3e | 8000 GB/s | yes | 97 tok/s4-bit quantization |
Tests quantized Mistral Large using Inferencer v2.5.1 on M3 Ultra 512GB across benchmarks, coding, logic, creative tasks, and compares Local vs Cloud performance.
Tests Mistral Large 4 across browser OS, C++, Blender, Godot, frontend design, FPS generation, Chrono City, and image-to-game tasks.
Tests Mistral Large 4, also known unofficially as ML4 and officially as le Chonk.