diff --git a/README.md b/README.md
index 3f6ebf15dc..013deb8dc3 100644
--- a/README.md
+++ b/README.md
@@ -53,7 +53,7 @@ With `[model] impl = "auto"` (the default), the trainer selects that custom stac
 | GLM-5 (`glm_moe_dsa`) | `zai-org/GLM-5`, `zai-org/GLM-5-FP8` | yes | ✅ | ✅ |
 | Qwen3 MoE (`qwen3_moe`) | `Qwen/Qwen3-30B-A3B`, … | yes | ✅ | ✅ |
 | Qwen3.5 MoE (`qwen3_5_moe`) | `Qwen/Qwen3.5-35B-A3B`, … | yes | ✅ | ✅ |
-| Qwen3 / Qwen3.5 VLMs | see [advanced.md](docs/advanced.md#multimodal-training) (`qwen3_vl`, `qwen3_5`, `qwen3_5_moe`) | MoE only on MoE VLMs | MoE only | ❌ |
+| Qwen3 / Qwen3.5 / Qwen3.8 VLMs | see [advanced.md](docs/advanced.md#multimodal-training) (`qwen3_vl`, `qwen3_5`, `qwen3_5_moe`) — Qwen3.8-27B reuses `qwen3_5` | MoE only on MoE VLMs | MoE only | ❌ |
 | Poolside Laguna (`laguna`) | `poolside/Laguna-XS.2` | yes | ✅ | ✅ |
 | MiniMax M2 (`minimax_m2`) | `MiniMax/MiniMax-M2` | yes | ✅ | ✅ |
 | Nemotron H (`nemotron_h`) | `nvidia/Nemotron-3-Nano-30B-A3B`, `nvidia/Nemotron-3-Super-120B-A12B`, … | yes | ✅ | ✅ |
diff --git a/deps/renderers b/deps/renderers
index bdb96b0c84..5520d1ece7 160000
--- a/deps/renderers
+++ b/deps/renderers
@@ -1 +1 @@
-Subproject commit bdb96b0c84a307e2b71c6a366c9d718c3ac7fe78
+Subproject commit 5520d1ece742ee25b50b97a579dbee70b1447c3f
diff --git a/deps/verifiers b/deps/verifiers
index 1f457da17a..2c93838a78 160000
--- a/deps/verifiers
+++ b/deps/verifiers
@@ -1 +1 @@
-Subproject commit 1f457da17a0408ef062f2c11576e67d2cd66126a
+Subproject commit 2c93838a782688c01ccbc5b4a292294bb4fa704f
diff --git a/docs/advanced.md b/docs/advanced.md
index c4c1ba9b9c..7f46da8e43 100644
--- a/docs/advanced.md
+++ b/docs/advanced.md
@@ -72,7 +72,7 @@ The built-in VLM registry covers:
 
 | Family | `model_type` | Vision attr | LM attr |
 |---|---|---|---|
-| Qwen3.5 | `qwen3_5` | `model.visual` | `model.language_model` |
+| Qwen3.5 / Qwen3.8 (dense) | `qwen3_5` | `model.visual` | `model.language_model` |
 | Qwen3.5-MoE | `qwen3_5_moe` | `model.visual` | `model.language_model` |
 
 ### Enabling VLM Mode
diff --git a/src/prime_rl/trainer/model.py b/src/prime_rl/trainer/model.py
index 1b564d515b..20bad4bd69 100644
--- a/src/prime_rl/trainer/model.py
+++ b/src/prime_rl/trainer/model.py
@@ -488,7 +488,11 @@ def get_model(
 
     is_vlm_training = config.vlm is not None
 
-    if "Qwen3.5" in config.name or "qwen3_5" in config.name.lower():
+    if (
+        "Qwen3.5" in config.name
+        or "Qwen3.8" in config.name
+        or "qwen3_5" in config.name.lower()
+    ):
         _patch_qwen3_5_text_position_ids()
         _patch_qwen3_5_moe_conversion_mapping()
         _patch_qwen3_5_linear_attn_varlen()
@@ -523,8 +527,10 @@ def get_model(
 
         _hub_kernels._kernels_enabled = True
 
-    # Fallback Qwen3.5 patch detection from loaded config model_type
-    if getattr(model_config, "model_type", "").startswith("qwen3_5_moe"):
+    # Fallback Qwen3.5 patch detection from loaded config model_type. Covers
+    # renamed Qwen3.5 / Qwen3.8 checkpoints (``qwen3_5``, ``qwen3_5_text``,
+    # ``qwen3_5_moe``) whose name_or_path misses the name-based gate above.
+    if getattr(model_config, "model_type", "").startswith("qwen3_5"):
         _patch_qwen3_5_text_position_ids()
         _patch_qwen3_5_moe_conversion_mapping()
         _patch_qwen3_5_linear_attn_varlen()