DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.
243.2K Pulls 1 Tag Updated 2 months ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
242.6K Pulls 1 Tag Updated 2 months ago
No Oficial 29 t/s en 8 VRAM - Calidad a escala fronteriza como GPT-5.5, DeepSeek-V4-pro y Kimi-K2.6.
85 Pulls 1 Tag Updated 14 hours ago
ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-Q4_K_XL
79 Pulls 1 Tag Updated 5 days ago
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4. + vision. ollama v.0.30.0-rc20 +
4,281 Pulls 1 Tag Updated 1 month ago
pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
3,050 Pulls 1 Tag Updated 2 months ago
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4.
1,929 Pulls 1 Tag Updated 2 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.
1,394 Pulls 5 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
965 Pulls 4 Tags Updated 1 year ago
Merged Unsloth's Dynamic Quantization
1,382 Pulls 1 Tag Updated 1 year ago
Latest DeepSeek_V3 model Q4
249 Pulls 1 Tag Updated 1 year ago
69 Pulls 1 Tag Updated 1 month ago