| Model profile | ||
|---|---|---|
| Model | Size | Approximate size |
| Ling 3.0 FlashModel source: provider262,144 tokens max native context | 124Bactive 5.1B | 74.4 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 |
| Radeon 8060S 96GB | 96 GBUnified RAM | 256 GB/s | yes | 33 tok/s4-bit quantization |
| DGX Spark | 128 GBUnified RAM | 273 GB/s | yes | 35 tok/s4-bit quantization |
| M5 Max | 128 GBUnified RAM | 614 GB/s | no | 74 tok/s4-bit quantization |
| M3 Ultra | 96 GBUnified RAM | 819 GB/s | no | 96 tok/s4-bit quantization |
| M5 Ultra | 256 GBUnified RAM | 1200 GB/s | no | 132 tok/s4-bit quantization |
| RTX PRO 6000 | 96 GBGPU VRAM | 1792 GB/s | yes | 179 tok/s4-bit quantization |
| DGX H200 | 1128 GBGPU HBM3e | 4800 GB/s | yes | 331 tok/s4-bit quantization |
| DGX Station | 748 GBCoherent Memory | 7100 GB/s | yes | 395 tok/s4-bit quantization |
| ET900N G3 | 748 GBCoherent Memory | 7100 GB/s | yes | 395 tok/s4-bit quantization |
| DGX B200 | 1440 GBGPU HBM3e | 8000 GB/s | yes | 414 tok/s4-bit quantization |
| GB200 NVL72 | 13400 GBGPU HBM3e | 8000 GB/s | yes | 414 tok/s4-bit quantization |
| GB300 NVL72 | 20000 GBGPU HBM3e | 8000 GB/s | yes | 414 tok/s4-bit quantization |
Tests Ling-3.0-flash-Sante, a healthcare-specialized model built on Ling-3.0-flash, through multiple evaluations and benchmarks.
Evaluates Ling-3.0-flash using Inferencer App v2.3.4 on M3 Ultra 512 GiB, noting its Kimi K3 attention architecture and origin from Qwen's sibling company.
Tests Ling 3.0 Flash performance on browser OS, C++ games, FPS, frontend, 3D CAD models, city timelines, and a C++ racing game.
Tests Ling-3.0-flash, a hybrid-reasoning MoE model designed for production-scale agentic applications.