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.
412K Pulls 2 Tags Updated 1 month ago
DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.
369.9K Pulls 2 Tags Updated 2 weeks ago
88 Pulls 1 Tag Updated 4 days ago
DeepSeek-V4-Flash 284B MoE (13B active), single-file IQ2_M merged from AtomicChat's GGUF shards so Ollama can pull it. ~33 tok/s on a 128 GB Apple Silicon Mac. Model by DeepSeek (MIT), quantization by AtomicChat.
373 Pulls 1 Tag Updated 2 weeks ago
DeepSeek-V4-Flash-Fast is a custom agent build based on DeepSeek-V4-Flash (Open Weights, Apache-2.0, MoE, ~285B total / ~20B active). Weights in low-bit quantization for fully CPU-only deployment:
273 Pulls 1 Tag Updated 3 weeks 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 +
5,875 Pulls 1 Tag Updated 3 months ago
pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
3,588 Pulls 1 Tag Updated 3 months ago
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4.
2,399 Pulls 1 Tag Updated 3 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.
938 Pulls 1 Tag Updated 1 month ago
To run DeepSeek-V4-Flash in full precision lossless, run Q4 (UD-Q4_K_XL), It is 155GB. vision tools thinking
661 Pulls 1 Tag Updated 1 month ago
A customized DeepSeek-V4-Pro
17 Pulls 1 Tag Updated 1 week ago
To run DeepSeek-V4-Flash in full precision lossless, run IQ1 (UD-IQ1_S), It is 82GB. vision tools thinking
270 Pulls 1 Tag Updated 1 month ago
ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-Q4_K_XL
278 Pulls 1 Tag Updated 1 month ago
To run DeepSeek-V4-Flash in full precision lossless, run Q3 (UD-Q3_K_M), It is 129 GB. vision tools thinking
127 Pulls 1 Tag Updated 1 month 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.
1,404 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
968 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
115 Pulls 1 Tag Updated 2 months ago