As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
1.3M Pulls 4 Tags Updated 1 week ago
A family of custom models built on **GLM-4.7-Flash** (MoE, 30B total / 3B active), tuned to act as autonomous coding agents — **each variant targeting a specific harness**
138 Pulls 1 Tag Updated 2 weeks ago
82.5K Pulls 5 Tags Updated 4 months ago
1,106 Pulls 5 Tags Updated 4 months ago
Privacidad, Rapidez, Muy bueno en todo incluido en agentes y sin censura 18GB
535 Pulls 1 Tag Updated 3 months ago
237 Pulls 1 Tag Updated 4 months ago
142 Pulls 1 Tag Updated 2 months ago
76 Pulls 4 Tags Updated 2 weeks ago
100 Pulls 1 Tag Updated 4 months ago
96 Pulls 1 Tag Updated 4 months ago
84 Pulls 1 Tag Updated 3 months ago
Glm-4.7-flash
53 Pulls 1 Tag Updated 3 months ago
26 Pulls 1 Tag Updated 2 months ago
17 Pulls 1 Tag Updated 1 month ago
Experimental version of glm-4.7-flash
19 Pulls 2 Tags Updated 4 months ago
11 Pulls 1 Tag Updated 4 months ago
Unsloth/GLM-4.7-Flash-REAP-23B-A3B model
1,856 Pulls 17 Tags Updated 4 months ago
This model was base on unsloth/GLM-4.7-Flash and trained on a small reasoning dataset of Claude Opus 4.5, with reasoning effort set to High.
1,066 Pulls 4 Tags Updated 4 months ago
A memory-efficient compressed variant of GLM-4.7-Flash that maintains near-identical performance while being 25% lighter.
769 Pulls 1 Tag Updated 4 months ago