Skip to content

Commit b12511f

Browse files
committed
docs: fix GPT-OSS-20B active params (3.6B, not dense 20B)
1 parent eba4bf5 commit b12511f

2 files changed

Lines changed: 2 additions & 2 deletions

File tree

docs-site/src/content/docs/integrations/local-llms.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -187,7 +187,7 @@ prompt). All models served via `llama-server`.
187187
| Model | Active Params | tg (tok/s) |
188188
|-------|--------------|------------|
189189
| **Gemma-4-26B-A4B** | **4B** | **~40** |
190-
| GPT-OSS-20B | 20B (dense) | ~17--38 |
190+
| GPT-OSS-20B | 3.6B | ~17--38 |
191191
| Qwen3-30B-A3B | 3B | ~15--27 |
192192
| GLM-4.7-Flash | 3B | ~12--13 |
193193
| Qwen3.5-35B-A3B | 3B | ~12 |

docs/local-llm-setup.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -99,7 +99,7 @@ prompt). All models served via `llama-server`.
9999
| Model | Active Params | tg (tok/s) |
100100
|-------|--------------|------------|
101101
| **Gemma-4-26B-A4B** | **4B** | **~40** |
102-
| GPT-OSS-20B | 20B (dense) | ~17--38 |
102+
| GPT-OSS-20B | 3.6B | ~17--38 |
103103
| Qwen3-30B-A3B | 3B | ~15--27 |
104104
| GLM-4.7-Flash | 3B | ~12--13 |
105105
| Qwen3.5-35B-A3B | 3B | ~12 |

0 commit comments

Comments
 (0)