chore(model gallery): add qwen3-30b-a1.5b-high-speed

gallery/index.yaml

@@ -442,6 +442,36 @@
     - filename: Smoothie-Qwen3-8B.Q4_K_M.gguf
       sha256: 36fc6df285c35beb8f1fdb46b3854bc4f420d3600afa397bf6a89e2ce5480112
       uri: huggingface://mradermacher/Smoothie-Qwen3-8B-GGUF/Smoothie-Qwen3-8B.Q4_K_M.gguf
+- !!merge <<: *qwen3
+  name: "qwen3-30b-a1.5b-high-speed"
+  icon: https://huggingface.co/DavidAU/Qwen3-30B-A1.5B-High-Speed/resolve/main/star-wars-hans-solo.gif
+  urls:
+    - https://huggingface.co/DavidAU/Qwen3-30B-A1.5B-High-Speed
+    - https://huggingface.co/mradermacher/Qwen3-30B-A1.5B-High-Speed-GGUF
+  description: |
+        This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.
+
+        This is a simple "finetune" of the Qwen's "Qwen 30B-A3B" (MOE) model, setting the experts in use from 8 to 4 (out of 128 experts).
+
+        This method close to doubles the speed of the model and uses 1.5B (of 30B) parameters instead of 3B (of 30B) parameters. Depending on the application you may want to use the regular model ("30B-A3B"), and use this model for simpler use case(s) although I did not notice any loss of function during routine (but not extensive) testing.
+
+        Example generation (Q4KS, CPU) at the bottom of this page using 4 experts / this model.
+
+        More complex use cases may benefit from using the normal version.
+
+        For reference:
+
+            Cpu only operation Q4KS (windows 11) jumps from 12 t/s to 23 t/s.
+            GPU performance IQ3S jumps from 75 t/s to over 125 t/s. (low to mid level card)
+
+        Context size: 32K + 8K for output (40k total)
+  overrides:
+    parameters:
+      model: Qwen3-30B-A1.5B-High-Speed.Q4_K_M.gguf
+  files:
+    - filename: Qwen3-30B-A1.5B-High-Speed.Q4_K_M.gguf
+      sha256: 2fca25524abe237483de64599bab54eba8fb22088fc21e30ba45ea8fb04dd1e0
+      uri: huggingface://mradermacher/Qwen3-30B-A1.5B-High-Speed-GGUF/Qwen3-30B-A1.5B-High-Speed.Q4_K_M.gguf
 - &gemma3
   url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
   name: "gemma-3-27b-it"
@@ -461,7 +491,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -479,7 +509,7 @@
   description: |
     google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
   overrides:
     #mmproj: gemma-3-12b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-12b-it-Q4_K_M.gguf
   files:
@@ -497,7 +527,7 @@
   description: |
     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
   overrides:
     #mmproj: gemma-3-4b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-4b-it-Q4_K_M.gguf
   files:
@@ -3398,7 +3428,7 @@
       sha256: b9f01bead9e163db9351af036d8d63ef479d7d48a1bb44934ead732a180f371c
       uri: huggingface://bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf
 - &qwen25
   name: "qwen2.5-14b-instruct" ## Qwen2.5
   icon: https://avatars.githubusercontent.com/u/141221163
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
   license: apache-2.0
@@ -5359,7 +5389,7 @@
       sha256: 0fec82625f74a9a340837de7af287b1d9042e5aeb70cda2621426db99958b0af
       uri: huggingface://bartowski/Chuluun-Qwen2.5-72B-v0.08-GGUF/Chuluun-Qwen2.5-72B-v0.08-Q4_K_M.gguf
 - &smollm
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## SmolLM
   name: "smollm-1.7b-instruct"
   icon: https://huggingface.co/datasets/HuggingFaceTB/images/resolve/main/banner_smol.png
   tags:
@@ -6825,7 +6855,7 @@
       sha256: cd92aff9b1e22f2a5eab28fb2d887e45fc3b1b03d5ed6ffca216832b8e5b9fb8
       uri: huggingface://mradermacher/WebThinker-QwQ-32B-i1-GGUF/WebThinker-QwQ-32B.i1-Q4_K_M.gguf
 - &llama31
   url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
   icon: https://avatars.githubusercontent.com/u/153379578
   name: "meta-llama-3.1-8b-instruct"
   license: llama3.1