⚡ 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
new activity about 2 hours ago
Jackrong/Qwopus3.6-27B-v2-FP8:hello,The model's output is garbled. updated a model about 3 hours ago
Jackrong/Qwopus3.6-27B-v2-FP8 updated a collection about 15 hours ago
🍎 Qwopus3.6Organizations
spaces 7
Running
6
Qwopus3.6-27B v1-preview Evaluation
🧪
Hands-on eval of Jackrong/Qwopus3.6-27B-v1-preview-GGUF
Running
3
Qwen3.6-27B Q5 Evaluation
🧪
Hands-on eval of Qwen3.6-27B Q5_K_XL on a 5090
Running on Zero
Agents
5
Qwopus3.5-27B-v3🏜️
🏜
Chat with a long‑context reasoning assistant
Running on Zero
Agents
6
Qwopus3.5-9B-v3🏃
🏃
Chat with a fast reasoning assistant
Running on Zero
Agents
30
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled
🧠
Chat with a long‑context reasoning assistant
Running on Zero
Agents
13
Qwen3.5 9B Claude 4.6 Opus Reasoning Distilled V2
🧠
Chat with a fast, long‑context reasoning assistant
models 218
Jackrong/Qwopus3.6-27B-v2-FP8
Image-Text-to-Text • 28B • Updated • 4
Jackrong/Qwopus3.6-35B-A3B-v1-MTP-GGUF
36B • Updated • 4
Jackrong/Qwopus3.6-27B-v2-GGUF
Image-Text-to-Text • 27B • Updated • 2.85k • 99
Jackrong/Qwopus3.6-27B-v2-MTP-GGUF
Text Generation • 27B • Updated • 3.53k • 66
Jackrong/Qwopus3.6-27B-v2
Image-Text-to-Text • 28B • Updated • 278 • 13
Jackrong/Qwopus3.6-27B-v2-MLX-8bit
Text Generation • 27B • Updated • 14 • 2
Jackrong/Qwopus3.6-27B-v2-MLX-6bit
Text Generation • 27B • Updated • 18 • 1
Jackrong/Qwopus3.6-27B-v2-MLX-4bit
Text Generation • 27B • Updated • 18 • 5
Jackrong/Qwopus3.5-4B-v3-MTP-GGUF
4B • Updated • 294 • 2
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-MTP-GGUF
9B • Updated • 386 • 6
datasets 29
Jackrong/Claude-opus-4.7-TraceInversion-5000x
Viewer • Updated • 4.76k • 204 • 6
Jackrong/Claude-opus-4.6-TraceInversion-9000x
Viewer • Updated • 8.67k • 230 • 11
Jackrong/DeepSeek-V4-Distill-8000x
Viewer • Updated • 7.72k • 11.2k • 83
Jackrong/GLM-5.1-Reasoning-1M-Cleaned
Viewer • Updated • 572k • 11.2k • 222
Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned
Viewer • Updated • 626k • 2.03k • 16
Jackrong/Competitive-Programming-python-blend
Viewer • Updated • 28.1k • 1.11k • 20
Jackrong/Qwen3.5-reasoning-700x
Viewer • Updated • 633 • 2.94k • 118
Jackrong/glm-4.7-multiturn-CoT
Viewer • Updated • 5.09k • 381 • 15
Jackrong/glm-4.7-Superior-Reasoning-stage1
Viewer • Updated • 1.76k • 179 • 5
Jackrong/MultiReason-ChatAlpaca
Viewer • Updated • 18.3k • 141 • 6