inclusionAI · inclusionai/ling-mini-2-0
| Provider | inclusionAI |
|---|---|
| Family | ling |
| Type | llm-chat |
| Status | active |
| Released | 2025-09-08 |
| Updated | 2026-04-13 |
| Parameters | 16.3B |
| Open weights | yes |
| Relationship | Model |
|---|---|
| Is a finetune of | inclusionAI/Ling-mini-base-2.0 |
Ordered by predicted speed. Bandwidth sets decode rate; memory decides whether it runs at all.
| Device | Memory | Bandwidth | Best quality | Weights | tok/s | Fastest |
|---|---|---|---|---|---|---|
| Cerebras WSE-3 | 44.0 GB | 21000000.0 GB/s | bf16 | 32.51 GB | ~5129532.5 | ~20518130.2 q4 |
| NVIDIA GB200 Grace Blackwell Superchip | 372.0 GB | 16000.0 GB/s | bf16 | 32.51 GB | ~3908.2 | ~15632.9 q4 |
| AMD Instinct MI355X | 288.0 GB | 8000.0 GB/s | bf16 | 32.51 GB | ~1954.1 | ~7816.4 q4 |
| NVIDIA B200 | 180.0 GB | 7700.0 GB/s | bf16 | 32.51 GB | ~1880.8 | ~7523.3 q4 |
| Google TPU7x (Ironwood) | 192.0 GB | 7380.0 GB/s | bf16 | 32.51 GB | ~1802.7 | ~7210.7 q4 |
| AMD Instinct MI325X | 256.0 GB | 6000.0 GB/s | bf16 | 32.51 GB | ~1465.6 | ~5862.3 q4 |
| AMD Instinct MI300X | 192.0 GB | 5300.0 GB/s | bf16 | 32.51 GB | ~1294.6 | ~5178.4 q4 |
| NVIDIA H200 SXM | 141.0 GB | 4800.0 GB/s | bf16 | 32.51 GB | ~1172.5 | ~4689.9 q4 |
| NVIDIA H100 NVL | 94.0 GB | 3900.0 GB/s | bf16 | 32.51 GB | ~952.6 | ~3810.5 q4 |
| NVIDIA H100 SXM | 80.0 GB | 3350.0 GB/s | bf16 | 32.51 GB | ~818.3 | ~3273.1 q4 |
| AMD Instinct MI250X | 128.0 GB | 3200.0 GB/s | bf16 | 32.51 GB | ~781.6 | ~3126.6 q4 |
| Google TPU v5p | 95.0 GB | 2765.0 GB/s | bf16 | 32.51 GB | ~675.4 | ~2701.6 q4 |
| NVIDIA A100 80GB SXM | 80.0 GB | 2039.0 GB/s | bf16 | 32.51 GB | ~498.1 | ~1992.2 q4 |
| NVIDIA H100 PCIe | 80.0 GB | 2000.0 GB/s | bf16 | 32.51 GB | ~488.5 | ~1954.1 q4 |
| NVIDIA GeForce RTX 5090 | 32.0 GB | 1792.0 GB/s | fp8 | 16.26 GB | ~875.4 | ~1750.9 q4 |
| Google TPU v6e (Trillium) | 32.0 GB | 1638.0 GB/s | fp8 | 16.26 GB | ~800.2 | ~1600.4 q4 |
| AMD Instinct MI210 | 64.0 GB | 1600.0 GB/s | bf16 | 32.51 GB | ~390.8 | ~1563.3 q4 |
| NVIDIA A100 40GB SXM | 40.0 GB | 1555.0 GB/s | fp8 | 16.26 GB | ~759.7 | ~1519.3 q4 |
| Google TPU v4 | 32.0 GB | 1200.0 GB/s | fp8 | 16.26 GB | ~586.2 | ~1172.5 q4 |
| NVIDIA GeForce RTX 4090 | 24.0 GB | 1008.0 GB/s | fp8 | 16.26 GB | ~492.4 | ~984.9 q4 |
| AMD Radeon RX 7900 XTX | 24.0 GB | 960.0 GB/s | fp8 | 16.26 GB | ~469.0 | ~938.0 q4 |
| NVIDIA GeForce RTX 5080 | 16.0 GB | 960.0 GB/s | q5 | 10.16 GB | ~750.4 | ~938.0 q4 |
| NVIDIA GeForce RTX 3090 | 24.0 GB | 936.0 GB/s | fp8 | 16.26 GB | ~457.3 | ~914.5 q4 |
| NVIDIA L40S | 48.0 GB | 864.0 GB/s | bf16 | 32.51 GB | ~211.0 | ~844.2 q4 |
| Apple M3 Ultra | 512.0 GB | 819.0 GB/s | bf16 | 32.51 GB | ~200.1 | ~800.2 q4 |
| AMD Radeon RX 7900 XT | 20.0 GB | 800.0 GB/s | q6 | 12.19 GB | ~521.1 | ~781.6 q4 |
| Apple M2 Ultra | 192.0 GB | 800.0 GB/s | bf16 | 32.51 GB | ~195.4 | ~781.6 q4 |
| Google TPU v5e | 16.0 GB | 800.0 GB/s | q5 | 10.16 GB | ~625.3 | ~781.6 q4 |
| NVIDIA GeForce RTX 4080 SUPER | 16.0 GB | 736.0 GB/s | q5 | 10.16 GB | ~575.3 | ~719.1 q4 |
| NVIDIA GeForce RTX 4070 Ti SUPER | 16.0 GB | 672.0 GB/s | q5 | 10.16 GB | ~525.3 | ~656.6 q4 |
| AMD Radeon RX 9070 XT | 16.0 GB | 640.0 GB/s | q5 | 10.16 GB | ~500.3 | ~625.3 q4 |
| Apple M4 Max | 128.0 GB | 546.0 GB/s | bf16 | 32.51 GB | ~133.4 | ~533.5 q4 |
| Apple M1 Max | 64.0 GB | 400.0 GB/s | bf16 | 32.51 GB | ~97.7 | ~390.8 q4 |
| Apple M2 Max | 96.0 GB | 400.0 GB/s | bf16 | 32.51 GB | ~97.7 | ~390.8 q4 |
| Apple M3 Max | 128.0 GB | 400.0 GB/s | bf16 | 32.51 GB | ~97.7 | ~390.8 q4 |
| NVIDIA GeForce RTX 3060 12GB | 12.0 GB | 360.0 GB/s | q4 | 8.13 GB | ~351.7 | ~351.7 q4 |
| NVIDIA L4 | 24.0 GB | 300.0 GB/s | fp8 | 16.26 GB | ~146.6 | ~293.1 q4 |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16.0 GB | 288.0 GB/s | q5 | 10.16 GB | ~225.1 | ~281.4 q4 |
| Apple M4 Pro | 64.0 GB | 273.0 GB/s | bf16 | 32.51 GB | ~66.7 | ~266.7 q4 |
| Apple M4 | 32.0 GB | 120.0 GB/s | fp8 | 16.26 GB | ~58.6 | ~117.2 q4 |
Taken from the card's availability section.
| Platform | Id on that platform |
|---|---|
| Hugging Face | inclusionAI/Ling-mini-2.0 |
| Benchmark | Evaluated as | Score | Evidence date | Source kind | |
|---|---|---|---|---|---|
| critpt | Ling-mini-2.0 | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| gpqa_diamond | Ling-mini-2.0 | 56.16% | 2026-09-10 evaluated | independent evaluator | source |
This card reports no benchmark scores yet.
| Benchmark | Catalogue standing | Score |
|---|