diff --git a/Models.md b/Models.md
index 034ae40..23c7419 100644
--- a/Models.md
+++ b/Models.md
@@ -6,19 +6,19 @@ All models are available via `api.nomyo.ai`. Pass the model ID string directly t
 
 | Model ID | Parameters | Type | ctx | Notes |
 |---|---|---|---|---|
-| `Qwen/Qwen3-0.6B` | 0.6B | General || Lightweight, fast inference |
-| `Qwen/Qwen3.5-0.8B` | 0.8B | General || Lightweight, fast inference |
-| `LiquidAI/LFM2.5-1.2B-Thinking` | 1.2B | Thinking || Reasoning model |
-| `ibm-granite/granite-4.0-h-small` | 32B | General || IBM Granite 4.0, enterprise-focused |
-| `Qwen/Qwen3.5-9B` | 9B | General || Balanced quality and speed |
+| `Qwen/Qwen3-0.6B` | 0.6B | General | 40k | Lightweight, fast inference |
+| `Qwen/Qwen3.5-0.8B` | 0.8B | General | 40k | Lightweight, fast inference |
+| `LiquidAI/LFM2.5-1.2B-Thinking` | 1.2B | Thinking | 4k | Reasoning model |
+| `ibm-granite/granite-4.0-h-small` | 32B | General | 131k | IBM Granite 4.0, enterprise-focused |
+| `Qwen/Qwen3.5-9B` | 9B | General | 200k | Balanced quality and speed |
 | `utter-project/EuroLLM-9B-Instruct-2512` | 9B | General | 32k | Multilingual, strong European language support |
 | `zai-org/GLM-4.7-Flash` | 30B (3B active) | General | 131k | Fast GLM variant |
-| `mistralai/Ministral-3-14B-Instruct-2512-GGUF` | 14B | General || Mistral instruction-tuned |
-| `ServiceNow-AI/Apriel-1.6-15b-Thinker` | 15B | Specialized || Reasoning model strong in math/physics/science |
+| `mistralai/Ministral-3-14B-Instruct-2512-GGUF` | 14B | General | 32k | Mistral instruction-tuned |
+| `ServiceNow-AI/Apriel-1.6-15b-Thinker` | 15B | Specialized | 32k | Reasoning model strong in math/physics/science |
 | `openai/gpt-oss-20b` | 20B | General | 131k | OpenAI open-weight release |
-| `LiquidAI/LFM2-24B-A2B` | 24B (2B active) | General || MoE — efficient inference |
-| `Qwen/Qwen3.5-27B` | 27B | General || High quality, large context |
-| `google/medgemma-27b-it` | 27B | Specialized || Medical domain, instruction-tuned |
+| `LiquidAI/LFM2-24B-A2B` | 24B (2B active) | General | 128k | MoE — efficient inference |
+| `Qwen/Qwen3.5-27B` | 27B | General | 200k | High quality, large context |
+| `google/medgemma-27b-it` | 27B | Specialized | 131k | Medical domain, instruction-tuned |
 | `nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4` | 30B (3B active) | General | 200k | MoE — efficient inference |
 | `Qwen/Qwen3.5-35B-A3B` | 35B (3B active) | General | 200k | MoE — efficient inference |
 | `moonshotai/Kimi-Linear-48B-A3B-Instruct` | 48B (3B active) | General | 1m | MoE — large capacity, efficient inference |