gpt-oss-120b vs Ling-3.0-flash
Specs, VRAM requirements and download trends — updated 24 October 2026.
openai · A · Open weights
Params
120.4 B
Context
131,072
30d
2.9 M
apache-2.0 · commercial OK
inclusionAI · B · Open weights
Params
127.5 B
Context
262,144
30d
10 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt-oss-120b | Ling-3.0-flash |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 120.4 B | 127.5 B |
| Architecture | GptOssForCausalLM | BailingMoeV3ForCausalLM |
| Context length | 131,072 | 262,144 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 2,891,100 | 9,544 |
| Downloads all time | 60.4 M | 44 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-08-04 | 2026-08-02 |
| API input price / 1M tokens | $0.15 | $0.021 |
| API output price / 1M tokens | $0.60 | $0.063 |
| Est. cost per 1M input + 1M output tokens | $0.75 | $0.084 |
| Cached input / 1M tokens | $0.075 | $0.0042 |
| AA Intelligence Index | 11.6 | 20.1 |
| AA Coding Index | 30.4 | 50.6 |
| AA Agentic Index | 3.7 | 19.3 |
| Max output tokens | 65,536 | 32,768 |
| API providers | 22 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gpt-oss-120b
$0.75
Ling-3.0-flash
$0.084
Ling-3.0-flash is 8.9× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
5.5 M10 K
gpt-oss-120b
Ling-3.0-flash
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gpt-oss-120b · fp16 @ 128K ctx
433.0 GB / 24 GB
Ling-3.0-flash · fp16 @ 256K ctx
892.9 GB / 24 GB