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.
424.3K 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.
381.5K Pulls 2 Tags Updated 3 weeks ago
An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
3.1M Pulls 64 Tags Updated 1 year ago
ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-Q4_K_XL
283 Pulls 1 Tag Updated 1 month 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.
465 Pulls 1 Tag Updated 3 weeks ago
202 Pulls 1 Tag Updated 1 week ago
67.5K Pulls 17 Tags Updated 2 weeks ago
173 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 +
6,017 Pulls 1 Tag Updated 3 months ago
pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
3,627 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.
2,435 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.
954 Pulls 1 Tag Updated 1 month ago
0731
1,053 Pulls 17 Tags Updated 2 weeks ago
A customized DeepSeek-V4-Pro
20 Pulls 1 Tag Updated 2 weeks ago
To run DeepSeek-V4-Flash in full precision lossless, run Q4 (UD-Q4_K_XL), It is 155GB. vision tools thinking
667 Pulls 1 Tag Updated 1 month ago
741 Pulls 1 Tag Updated 2 months 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:
327 Pulls 1 Tag Updated 1 month ago
To run DeepSeek-V4-Flash in full precision lossless, run IQ1 (UD-IQ1_S), It is 82GB. vision tools thinking
282 Pulls 1 Tag Updated 1 month ago
297 Pulls 1 Tag Updated 1 month ago
377 Pulls 1 Tag Updated 2 months ago