deepseek-v3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

671b

3.8M Pulls 5 Tags Updated 1 year ago

deepseek-v3.1

DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

tools thinking 671b

726.9K Pulls 7 Tags Updated 11 months ago

fhagenciadigital/ds-go-pro

Senior Go & SpecKit engineering agent powered by DeepSeek-v3.1 671B, optimized for idiomatic development and deterministic BDD testing.

cloud

140 Pulls 1 Tag Updated 5 months ago

zerocopia/deepseek-v3.2

tools thinking cloud

103 Pulls 1 Tag Updated 4 months ago

drivedenpadev/deepseek-v3.2

tools

3,420 Pulls 1 Tag Updated 8 months ago

zerocopia/deepseek-v3.1

tools thinking cloud

38 Pulls 1 Tag Updated 4 months ago

huihui_ai/deepseek-v3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

7,196 Pulls 2 Tags Updated 1 year ago

huihui_ai/deepseek-v3-abliterated

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

671b

4,108 Pulls 5 Tags Updated 1 year ago

ukjin/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill

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.

tools thinking 4b

2,373 Pulls 2 Tags Updated 1 year ago

milkey/deepseek-v3-UD

(Unsloth Dynamic Quants) A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

2,064 Pulls 3 Tags Updated 1 year ago

huihui_ai/deepseek-v3-pruned

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.

411b

1,407 Pulls 5 Tags Updated 1 year ago