DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
700.3K Pulls 8 Tags Updated 6 months ago
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
3.8M Pulls 5 Tags Updated 1 year ago
Senior Go & SpecKit engineering agent powered by DeepSeek-v3.1 671B, optimized for idiomatic development and deterministic BDD testing.
85 Pulls 1 Tag Updated 2 months ago
This model is a distilled version of Qwen/Qwen3-30B-A3B-Instruct designed to inherit the reasoning and behavioral characteristics of its much larger teacher model, deepseek-ai/DeepSeek-V3.1.
2,026 Pulls 2 Tags Updated 9 months ago
19 Pulls 1 Tag Updated 1 month ago
This is not the ablation version. DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode.
234 Pulls 3 Tags Updated 9 months ago
139 Pulls 2 Tags Updated 9 months ago
14 Pulls 1 Tag Updated 9 months ago
DeepSeek-V3-Pruned-Coder-411B is a pruned version of the DeepSeek-V3 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.
1,390 Pulls 5 Tags Updated 1 year ago
7,186 Pulls 2 Tags Updated 1 year ago
3,929 Pulls 5 Tags Updated 1 year ago
(Unsloth Dynamic Quants) A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
2,063 Pulls 3 Tags Updated 1 year ago
DeepSeep V3 from March 2025 Merged from Unsloth's HF - 671B params - Q8_0/713 GB & Q4_K_M/404 GB
959 Pulls 4 Tags Updated 1 year ago
Single file version with (Dynamic Quants) A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
114 Pulls 4 Tags Updated 1 year ago
23 Pulls 1 Tag Updated 1 year ago