← back to Exo
feat: only show thinking toggle for models that support it (#1497)
6c322ebb72c251ad0c8cd38c9009d5ae60ad7f07 · 2026-02-18 09:05:00 -0800 · Alex Cheema
## Summary
- Adds `thinking_toggle` capability to 26 model cards that support
toggling thinking mode on/off
- GPT-OSS models (20b, 120b) excluded — they always think and don't
support toggling
- Dashboard UI updated to check for `thinking_toggle` capability before
showing the toggle button
## Test plan
- [x] `uv run basedpyright` — 0 errors
- [x] `uv run ruff check` — all checks passed
- [x] `nix fmt` — 0 files changed
- [x] `uv run pytest` — 188 passed, 0 failed
- [x] Security review passed (no secrets, eval/exec, innerHTML, or dep
changes)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Files touched
M dashboard/src/lib/components/ChatForm.svelteM resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.tomlM resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.tomlM resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.tomlM resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.tomlM resources/inference_model_cards/mlx-community--GLM-4.7-4bit.tomlM resources/inference_model_cards/mlx-community--GLM-4.7-6bit.tomlM resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.tomlM resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.tomlM resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.tomlM resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.tomlM resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.tomlM resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.tomlM resources/inference_model_cards/mlx-community--Kimi-K2.5.tomlM resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.tomlM resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.tomlM resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.tomlM resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.tomlM resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.tomlM resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml
Diff
commit 6c322ebb72c251ad0c8cd38c9009d5ae60ad7f07
Author: Alex Cheema <41707476+AlexCheema@users.noreply.github.com>
Date: Wed Feb 18 09:05:00 2026 -0800
feat: only show thinking toggle for models that support it (#1497)
## Summary
- Adds `thinking_toggle` capability to 26 model cards that support
toggling thinking mode on/off
- GPT-OSS models (20b, 120b) excluded — they always think and don't
support toggling
- Dashboard UI updated to check for `thinking_toggle` capability before
showing the toggle button
## Test plan
- [x] `uv run basedpyright` — 0 errors
- [x] `uv run ruff check` — all checks passed
- [x] `nix fmt` — 0 files changed
- [x] `uv run pytest` — 188 passed, 0 failed
- [x] Security review passed (no secrets, eval/exec, innerHTML, or dep
changes)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
---
dashboard/src/lib/components/ChatForm.svelte | 2 +-
resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml | 2 +-
resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml | 2 +-
resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml | 2 +-
resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml | 2 +-
resources/inference_model_cards/mlx-community--Kimi-K2.5.toml | 2 +-
resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml | 2 +-
resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml | 2 +-
resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml | 2 +-
resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml | 2 +-
.../mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml | 2 +-
.../mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml | 2 +-
resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml | 2 +-
resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml | 2 +-
.../mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml | 2 +-
.../mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml | 2 +-
resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml | 2 +-
resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml | 2 +-
resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml | 2 +-
27 files changed, 27 insertions(+), 27 deletions(-)
diff --git a/dashboard/src/lib/components/ChatForm.svelte b/dashboard/src/lib/components/ChatForm.svelte
index 2eb7aa40..6ccba979 100644
--- a/dashboard/src/lib/components/ChatForm.svelte
+++ b/dashboard/src/lib/components/ChatForm.svelte
@@ -103,7 +103,7 @@
const modelSupportsThinking = $derived(() => {
if (!currentModel) return false;
const caps = modelCapabilities[currentModel] || [];
- return caps.includes("thinking") && caps.includes("text");
+ return caps.includes("thinking_toggle") && caps.includes("text");
});
const isEditOnlyWithoutImage = $derived(
diff --git a/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml b/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml
index 41784cf6..2c982882 100644
--- a/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "deepseek"
quantization = "4bit"
base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 405874409472
diff --git a/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml b/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml
index a5d77bcd..4cf99bec 100644
--- a/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "deepseek"
quantization = "8bit"
base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 765577920512
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml b/resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml
index a7acea44..0f8708bc 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "8bit"
base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 122406567936
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml b/resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml
index 4258c225..764372fd 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "bf16"
base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 229780750336
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml b/resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml
index 0672d664..559cea65 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "4bit"
base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 198556925568
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml b/resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml
index bcf1cae4..bdcd0b4e 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "6bit"
base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 286737579648
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml b/resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml
index 0f56c2f7..1d942440 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "8bit"
base_model = "GLM 4.7"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 396963397248
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml
index 8637cef0..2aad9b5b 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "4bit"
base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 19327352832
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml
index b9a9da4d..1efed44f 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "5bit"
base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 22548578304
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml
index e3cb1fa8..b5ec0fa5 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "6bit"
base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 26843545600
diff --git a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml
index bd6df312..4b400aeb 100644
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "8bit"
base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 34359738368
diff --git a/resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml b/resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml
index 0a955b04..3e7dedd2 100644
--- a/resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml
+++ b/resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "kimi"
quantization = ""
base_model = "Kimi K2"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 706522120192
diff --git a/resources/inference_model_cards/mlx-community--Kimi-K2.5.toml b/resources/inference_model_cards/mlx-community--Kimi-K2.5.toml
index 806c6b30..eb73ea09 100644
--- a/resources/inference_model_cards/mlx-community--Kimi-K2.5.toml
+++ b/resources/inference_model_cards/mlx-community--Kimi-K2.5.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "kimi"
quantization = ""
base_model = "Kimi K2.5"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 662498705408
diff --git a/resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml b/resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml
index 92ec6746..f740e0d5 100644
--- a/resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml
+++ b/resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "minimax"
quantization = "3bit"
base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 100086644736
diff --git a/resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml b/resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml
index c1388d2f..6cf55637 100644
--- a/resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "minimax"
quantization = "8bit"
base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 242986745856
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml
index 7929aaba..03c6c28b 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "4bit"
base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 342884352
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml
index d9fcc368..44177385 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "8bit"
base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 698351616
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml
index ef835c6a..e8ef3494 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "4bit"
base_model = "Qwen3 235B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 141733920768
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml
index f6e079ab..1ce1fd62 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "8bit"
base_model = "Qwen3 235B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 268435456000
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml
index 48a6666f..bcae53f9 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "4bit"
base_model = "Qwen3 30B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 17612931072
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml
index c283396f..ed08db63 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "8bit"
base_model = "Qwen3 30B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 33279705088
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml
index 2a3e3c19..48caa3fc 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "4bit"
base_model = "Qwen3 Next 80B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 47080074240
diff --git a/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml b/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml
index 65d33253..bd4ae549 100644
--- a/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "8bit"
base_model = "Qwen3 Next 80B"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 88814387200
diff --git a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml
index 9c12a5b9..78385661 100644
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "step"
quantization = "4bit"
base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 114572190076
diff --git a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml
index d564498a..ab336bc2 100644
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "step"
quantization = "6bit"
base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 159039627774
diff --git a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml
index afef6d7f..ef2a5074 100644
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "step"
quantization = "8bit"
base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
+capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 209082699847
← 2ebe6216 feat: add explicit --offline mode for air-gapped clusters (#
·
back to Exo
·
Fix tool calling (#1529) c2f2111b →