Qwen3.5 2B in Q8_0 quantization. Strong balance of capability and efficiency with 262K context, vision, tool use, and thinking. Ideal for local deployment on consumer hardware.
271 Pulls 1 Tag Updated 2 months ago
A compact Havenlon-focused Qwen3.5 2B model for execution control, intent-to-action reasoning, policy boundaries, and AI Agent execution risk.
65 Pulls 1 Tag Updated 1 month ago
WSAI-Heart-Pro 是 WSAI-Heart 系列的 Pro 级正式版本，基于 Qwen3.5-2B-Base 全精度 LoRA 微调。约 2B 参数，端侧部署友好。
72 Pulls 1 Tag Updated 4 months ago
WSAI-Heart-Pro-Exp 是 WSAI-Heart-Pro 的实验版本，基于 Qwen3.5-2B-Base 进行全精度 LoRA 微调。相比0.8B，这次升级到了 2B 参数，共情表达与对话质量均有明显提升，且仍然可以端侧部署。
36 Pulls 1 Tag Updated 4 months ago
测试用
35 Pulls 1 Tag Updated 5 months ago
26.3.7. Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.
1,081 Pulls 1 Tag Updated 6 months ago
Qwen3.5 2B LoRA trained to act like Rocky from Project Hail Mary by Andy Weir.
22 Pulls 1 Tag Updated 4 months ago
3 Pulls 1 Tag Updated yesterday
15 Pulls 1 Tag Updated 3 weeks ago
13 Pulls 1 Tag Updated 4 weeks ago
9 Pulls 1 Tag Updated 2 weeks ago
7 Pulls 1 Tag Updated 1 week ago
7 Pulls 1 Tag Updated 3 weeks ago
5 Pulls 1 Tag Updated 4 weeks ago
3 Pulls 1 Tag Updated 3 weeks ago
3 Pulls 1 Tag Updated 4 weeks ago
mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic-GGUF
4,116 Pulls 2 Tags Updated 5 months ago
Quantization based on Jackrong / Qwen3.5-27B-GLM5.1-Distill-v1
229 Pulls 1 Tag Updated 5 months ago
26.3.7. Qwen3.5-27B-Q4 Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.
11.4K Pulls 1 Tag Updated 6 months ago
6,507 Pulls 2 Tags Updated 6 months ago