inclusionAI · inclusionai/ling-3-0-tiny
| Provider | inclusionAI |
|---|---|
| Family | ling |
| Type | llm-chat |
| Status | active |
| Released | 2026-08-10 |
| Updated | 2026-09-04 |
| Parameters | 7.9B |
| Open weights | yes |
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 | 15.79 GB | ~931158.5 | ~3724634.1 q4 |
| NVIDIA GB200 Grace Blackwell Superchip | 372.0 GB | 16000.0 GB/s | bf16 | 15.79 GB | ~709.5 | ~2837.8 q4 |
| AMD Instinct MI355X | 288.0 GB | 8000.0 GB/s | bf16 | 15.79 GB | ~354.7 | ~1418.9 q4 |
| NVIDIA B200 | 180.0 GB | 7700.0 GB/s | bf16 | 15.79 GB | ~341.4 | ~1365.7 q4 |
| Google TPU7x (Ironwood) | 192.0 GB | 7380.0 GB/s | bf16 | 15.79 GB | ~327.2 | ~1308.9 q4 |
| AMD Instinct MI325X | 256.0 GB | 6000.0 GB/s | bf16 | 15.79 GB | ~266.0 | ~1064.2 q4 |
| AMD Instinct MI300X | 192.0 GB | 5300.0 GB/s | bf16 | 15.79 GB | ~235.0 | ~940.0 q4 |
| NVIDIA H200 SXM | 141.0 GB | 4800.0 GB/s | bf16 | 15.79 GB | ~212.8 | ~851.3 q4 |
| NVIDIA H100 NVL | 94.0 GB | 3900.0 GB/s | bf16 | 15.79 GB | ~172.9 | ~691.7 q4 |
| NVIDIA H100 SXM | 80.0 GB | 3350.0 GB/s | bf16 | 15.79 GB | ~148.5 | ~594.2 q4 |
| AMD Instinct MI250X | 128.0 GB | 3200.0 GB/s | bf16 | 15.79 GB | ~141.9 | ~567.6 q4 |
| Google TPU v5p | 95.0 GB | 2765.0 GB/s | bf16 | 15.79 GB | ~122.6 | ~490.4 q4 |
| NVIDIA A100 80GB SXM | 80.0 GB | 2039.0 GB/s | bf16 | 15.79 GB | ~90.4 | ~361.6 q4 |
| NVIDIA H100 PCIe | 80.0 GB | 2000.0 GB/s | bf16 | 15.79 GB | ~88.7 | ~354.7 q4 |
| NVIDIA GeForce RTX 5090 | 32.0 GB | 1792.0 GB/s | bf16 | 15.79 GB | ~79.5 | ~317.8 q4 |
| Google TPU v6e (Trillium) | 32.0 GB | 1638.0 GB/s | bf16 | 15.79 GB | ~72.6 | ~290.5 q4 |
| AMD Instinct MI210 | 64.0 GB | 1600.0 GB/s | bf16 | 15.79 GB | ~70.9 | ~283.8 q4 |
| NVIDIA A100 40GB SXM | 40.0 GB | 1555.0 GB/s | bf16 | 15.79 GB | ~69.0 | ~275.8 q4 |
| Google TPU v4 | 32.0 GB | 1200.0 GB/s | bf16 | 15.79 GB | ~53.2 | ~212.8 q4 |
| NVIDIA GeForce RTX 4090 | 24.0 GB | 1008.0 GB/s | bf16 | 15.79 GB | ~44.7 | ~178.8 q4 |
| AMD Radeon RX 7900 XTX | 24.0 GB | 960.0 GB/s | bf16 | 15.79 GB | ~42.6 | ~170.3 q4 |
| NVIDIA GeForce RTX 5080 | 16.0 GB | 960.0 GB/s | fp8 | 7.89 GB | ~85.1 | ~170.3 q4 |
| NVIDIA GeForce RTX 3090 | 24.0 GB | 936.0 GB/s | bf16 | 15.79 GB | ~41.5 | ~166.0 q4 |
| NVIDIA L40S | 48.0 GB | 864.0 GB/s | bf16 | 15.79 GB | ~38.3 | ~153.2 q4 |
| Apple M3 Ultra | 512.0 GB | 819.0 GB/s | bf16 | 15.79 GB | ~36.3 | ~145.3 q4 |
| AMD Radeon RX 7900 XT | 20.0 GB | 800.0 GB/s | fp8 | 7.89 GB | ~70.9 | ~141.9 q4 |
| Apple M2 Ultra | 192.0 GB | 800.0 GB/s | bf16 | 15.79 GB | ~35.5 | ~141.9 q4 |
| Google TPU v5e | 16.0 GB | 800.0 GB/s | fp8 | 7.89 GB | ~70.9 | ~141.9 q4 |
| NVIDIA GeForce RTX 4080 SUPER | 16.0 GB | 736.0 GB/s | fp8 | 7.89 GB | ~65.3 | ~130.5 q4 |
| NVIDIA GeForce RTX 4070 Ti SUPER | 16.0 GB | 672.0 GB/s | fp8 | 7.89 GB | ~59.6 | ~119.2 q4 |
| AMD Radeon RX 9070 XT | 16.0 GB | 640.0 GB/s | fp8 | 7.89 GB | ~56.8 | ~113.5 q4 |
| Apple M4 Max | 128.0 GB | 546.0 GB/s | bf16 | 15.79 GB | ~24.2 | ~96.8 q4 |
| Apple M1 Max | 64.0 GB | 400.0 GB/s | bf16 | 15.79 GB | ~17.7 | ~70.9 q4 |
| Apple M2 Max | 96.0 GB | 400.0 GB/s | bf16 | 15.79 GB | ~17.7 | ~70.9 q4 |
| Apple M3 Max | 128.0 GB | 400.0 GB/s | bf16 | 15.79 GB | ~17.7 | ~70.9 q4 |
| NVIDIA GeForce RTX 3060 12GB | 12.0 GB | 360.0 GB/s | fp8 | 7.89 GB | ~31.9 | ~63.9 q4 |
| NVIDIA L4 | 24.0 GB | 300.0 GB/s | bf16 | 15.79 GB | ~13.3 | ~53.2 q4 |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16.0 GB | 288.0 GB/s | fp8 | 7.89 GB | ~25.5 | ~51.1 q4 |
| Apple M4 Pro | 64.0 GB | 273.0 GB/s | bf16 | 15.79 GB | ~12.1 | ~48.4 q4 |
| Apple M4 | 32.0 GB | 120.0 GB/s | bf16 | 15.79 GB | ~5.3 | ~21.3 q4 |
Taken from the card's availability section.
| Platform | Id on that platform |
|---|---|
| Hugging Face | inclusionAI/Ling-3.0-tiny |
| Benchmark | Evaluated as | Score | Evidence date | Source kind | |
|---|---|---|---|---|---|
| aa_lcr | Ling 3.0 Tiny | 60.33% | 2026-09-10 evaluated | independent evaluator | source |
| critpt | Ling 3.0 Tiny | 0.0% | 2026-09-10 evaluated | independent evaluator | source |
| gdpval_aa | Ling 3.0 Tiny | 10.78% | 2026-09-10 evaluated | independent evaluator | source |
| gpqa_diamond | Ling 3.0 Tiny | 73.43% | 2026-09-10 evaluated | independent evaluator | source |
| scicode | Ling 3.0 Tiny | 24.19% | 2026-09-10 evaluated | independent evaluator | source |
This card reports no benchmark scores yet.
| Benchmark | Catalogue standing | Score |
|---|