From ed74d0cbeab4e64aa1b8a5116e584be3deefbbd0 Mon Sep 17 00:00:00 2001 From: dbrian57 Date: Mon, 16 Mar 2026 12:18:51 -0400 Subject: [PATCH] Adds a new Qwen model to Training docs --- training/serverless-rl/available-models.mdx | 1 + 1 file changed, 1 insertion(+) diff --git a/training/serverless-rl/available-models.mdx b/training/serverless-rl/available-models.mdx index 8fa3d1a22f..32107640ff 100644 --- a/training/serverless-rl/available-models.mdx +++ b/training/serverless-rl/available-models.mdx @@ -13,3 +13,4 @@ To express interest in a particular model, contact [support](mailto:support@wand | --------------------------- | ---------------------------------- | ---- | -------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | | OpenPipe Qwen3 14B Instruct | `OpenPipe/Qwen3-14B-Instruct` | Text | 32.8K | 14.8B (Total) | An efficient multilingual, dense, instruction-tuned model, optimized by OpenPipe for building agents with finetuning. | | Qwen3 30B A3B | `Qwen/Qwen3-30B-A3B-Instruct-2507` | Text | 262K | 3.3B-30.5B (Active-Total) | Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding. | +| Qwen3.5 35B A3B | `Qwen/Qwen3.5-35B-A3B` | Text | 262K | 3B-36B (Active-Total) | A multimodal MoE model with 256 experts (8 routed + 1 shared active) combining vision-language understanding, agentic tool use, and 201-language support. | \ No newline at end of file