⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy.
Jackrong PRO
Jackrong
AI & ML interests
None yet
Recent Activity
updated a model 1 day ago
Jackrong/Qwopus3.6-27B-v2-GGUF updated a model 1 day ago
Jackrong/Qwopus3.5-9B-Coder-GGUF updated a model 1 day ago
Jackrong/Qwopus3.6-35B-A3B-v1-GGUFOrganizations
-
Jackrong/Negentropy-claude-opus-4.7-9B
Image-Text-to-Text • 9B • Updated • 1.8k • 21 -
Jackrong/Negentropy-claude-opus-4.7-9B-GGUF
Image-Text-to-Text • 9B • Updated • 25.3k • 51 -
Jackrong/Negentropy-claude-opus-4.7-4B
Image-Text-to-Text • 5B • Updated • 494 • 11 -
Jackrong/Negentropy-claude-opus-4.7-4B-GGUF
Image-Text-to-Text • 4B • Updated • 9.2k • 17
-
Jackrong/Qwen3.5-27B-GLM5.1-Distill-v1
Image-Text-to-Text • 27B • Updated • 189 • 5 -
Jackrong/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF
Image-Text-to-Text • 27B • Updated • 3.13k • 16 -
Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1
Image-Text-to-Text • 10B • Updated • 20.8k • 62 -
Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1-GGUF
Image-Text-to-Text • 9B • Updated • 174k • 101
🪐 A curated collection of lightweight multimodal Gemopus-4 models designed for edge deployment.
-
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2
Image-Text-to-Text • 28B • Updated • 590k • 122 -
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF
Image-Text-to-Text • 27B • Updated • 84.7k • 605 -
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2
Image-Text-to-Text • 10B • Updated • 4.46k • 167 -
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF
Image-Text-to-Text • 9B • Updated • 114k • 355
-
Jackrong/Qwen3.5-27B-Gemini-3.1-Pro-Reasoning-Distill
Text Generation • 28B • Updated • 35 • 5 -
Jackrong/Qwen3.5-27B-Gemini-3.1-Pro-Reasoning-Distill-GGUF
Text Generation • 27B • Updated • 1.52k • 8 -
Jackrong/Qwen3.5-9B-Gemini-3.1-Pro-Reasoning-Distill
Text Generation • 10B • Updated • 14 • 6 -
Jackrong/Qwen3.5-9B-Gemini-3.1-Pro-Reasoning-Distill-GGUF
Text Generation • 9B • Updated • 9.31k • 30
-
Jackrong/GPT-5-Distill-Qwen3-4B-Instruct
4B • Updated • 516 • 5 -
Jackrong/GPT-5-Distill-Qwen3-4B-Instruct-GGUF
4B • Updated • 3.55k • 17 -
Jackrong/GPT-5-Distill-llama3.1-8B-Instruct-GGUF
Text Generation • 8B • Updated • 148 -
Jackrong/GPT-5-Distill-llama3.2-3B-Instruct
Text Generation • 3B • Updated • 269 • • 3
This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e
-
Jackrong/Qwopus3.6-27B-v2
Image-Text-to-Text • 28B • Updated • 3.13k • 18 -
Jackrong/Qwopus3.6-27B-v2-GGUF
Image-Text-to-Text • 27B • Updated • 12.7k • 128 -
Jackrong/Qwopus3.6-27B-v2-FP8
Image-Text-to-Text • 28B • Updated • 863 • 8 -
Jackrong/Qwopus3.6-35B-A3B-v1
Image-Text-to-Text • 36B • Updated • 11.9k • 41
-
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash
Image-Text-to-Text • 10B • Updated • 5.56k • 25 -
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
Image-Text-to-Text • 9B • Updated • 480k • 181 -
Jackrong/MLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bit
Text Generation • 1B • Updated • 7.06k • 9 -
Jackrong/MLX-Qwen3.5-9B-DeepSeek-V4-Flash-6bit
Text Generation • 9B • Updated • 2.7k • 2
🌟Qwopus3.5-v3.5 is the latest model in the Claude series.
-
Jackrong/Qwopus3.5-27B-v3.5
Image-Text-to-Text • 27B • Updated • 2.93k • 16 -
Jackrong/Qwopus3.5-27B-v3.5-GGUF
Image-Text-to-Text • 27B • Updated • 7.14k • 43 -
Jackrong/Qwopus3.5-27B-v3
Image-Text-to-Text • 27B • Updated • 1.58k • 234 -
Jackrong/Qwopus3.5-27B-v3-GGUF
Image-Text-to-Text • 27B • Updated • 13.2k • 352
-
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
Image-Text-to-Text • 28B • Updated • 190k • • 2.85k -
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF
Image-Text-to-Text • 27B • Updated • 322k • 656 -
Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Text Generation • 36B • Updated • 834 • 129 -
Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled
Image-Text-to-Text • 5B • Updated • 940 • 29
⚡ MTP (Multi Token Prediction) speculative decoding enables models like Qwen3.6 to have ~1.4-2.2x faster generation with no change in accuracy.
This collection features the advanced Qwopus3.6 series of multimodal large models, which are fine-tuned from the Qwen3.6 base models with a focus on e
-
Jackrong/Qwopus3.6-27B-v2
Image-Text-to-Text • 28B • Updated • 3.13k • 18 -
Jackrong/Qwopus3.6-27B-v2-GGUF
Image-Text-to-Text • 27B • Updated • 12.7k • 128 -
Jackrong/Qwopus3.6-27B-v2-FP8
Image-Text-to-Text • 28B • Updated • 863 • 8 -
Jackrong/Qwopus3.6-35B-A3B-v1
Image-Text-to-Text • 36B • Updated • 11.9k • 41
-
Jackrong/Negentropy-claude-opus-4.7-9B
Image-Text-to-Text • 9B • Updated • 1.8k • 21 -
Jackrong/Negentropy-claude-opus-4.7-9B-GGUF
Image-Text-to-Text • 9B • Updated • 25.3k • 51 -
Jackrong/Negentropy-claude-opus-4.7-4B
Image-Text-to-Text • 5B • Updated • 494 • 11 -
Jackrong/Negentropy-claude-opus-4.7-4B-GGUF
Image-Text-to-Text • 4B • Updated • 9.2k • 17
-
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash
Image-Text-to-Text • 10B • Updated • 5.56k • 25 -
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
Image-Text-to-Text • 9B • Updated • 480k • 181 -
Jackrong/MLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bit
Text Generation • 1B • Updated • 7.06k • 9 -
Jackrong/MLX-Qwen3.5-9B-DeepSeek-V4-Flash-6bit
Text Generation • 9B • Updated • 2.7k • 2
-
Jackrong/Qwen3.5-27B-GLM5.1-Distill-v1
Image-Text-to-Text • 27B • Updated • 189 • 5 -
Jackrong/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF
Image-Text-to-Text • 27B • Updated • 3.13k • 16 -
Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1
Image-Text-to-Text • 10B • Updated • 20.8k • 62 -
Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1-GGUF
Image-Text-to-Text • 9B • Updated • 174k • 101
🌟Qwopus3.5-v3.5 is the latest model in the Claude series.
-
Jackrong/Qwopus3.5-27B-v3.5
Image-Text-to-Text • 27B • Updated • 2.93k • 16 -
Jackrong/Qwopus3.5-27B-v3.5-GGUF
Image-Text-to-Text • 27B • Updated • 7.14k • 43 -
Jackrong/Qwopus3.5-27B-v3
Image-Text-to-Text • 27B • Updated • 1.58k • 234 -
Jackrong/Qwopus3.5-27B-v3-GGUF
Image-Text-to-Text • 27B • Updated • 13.2k • 352
🪐 A curated collection of lightweight multimodal Gemopus-4 models designed for edge deployment.
-
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
Image-Text-to-Text • 28B • Updated • 190k • • 2.85k -
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF
Image-Text-to-Text • 27B • Updated • 322k • 656 -
Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Text Generation • 36B • Updated • 834 • 129 -
Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled
Image-Text-to-Text • 5B • Updated • 940 • 29
-
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2
Image-Text-to-Text • 28B • Updated • 590k • 122 -
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF
Image-Text-to-Text • 27B • Updated • 84.7k • 605 -
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2
Image-Text-to-Text • 10B • Updated • 4.46k • 167 -
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF
Image-Text-to-Text • 9B • Updated • 114k • 355
-
Jackrong/Qwen3.5-27B-Gemini-3.1-Pro-Reasoning-Distill
Text Generation • 28B • Updated • 35 • 5 -
Jackrong/Qwen3.5-27B-Gemini-3.1-Pro-Reasoning-Distill-GGUF
Text Generation • 27B • Updated • 1.52k • 8 -
Jackrong/Qwen3.5-9B-Gemini-3.1-Pro-Reasoning-Distill
Text Generation • 10B • Updated • 14 • 6 -
Jackrong/Qwen3.5-9B-Gemini-3.1-Pro-Reasoning-Distill-GGUF
Text Generation • 9B • Updated • 9.31k • 30
-
Jackrong/GPT-5-Distill-Qwen3-4B-Instruct
4B • Updated • 516 • 5 -
Jackrong/GPT-5-Distill-Qwen3-4B-Instruct-GGUF
4B • Updated • 3.55k • 17 -
Jackrong/GPT-5-Distill-llama3.1-8B-Instruct-GGUF
Text Generation • 8B • Updated • 148 -
Jackrong/GPT-5-Distill-llama3.2-3B-Instruct
Text Generation • 3B • Updated • 269 • • 3