deepseek v4 flash

deepseek-v4-flash

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.

tools thinking cloud

424.3K Pulls 2 Tags Updated 1 month ago

seansandwich22/deepseekV4

ollama run hf.co/unsloth/DeepSeek-V4-Flash-GGUF:UD-Q4_K_XL

tools

283 Pulls 1 Tag Updated 1 month ago

bluehawana/deepseek-v4-flash

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

lcz2026/Qwen3.5-DeepSeek-V4-9B-Flash

202 Pulls 1 Tag Updated 1 week ago

frob/deepseek-v4-flash-0731

284b

67.5K Pulls 17 Tags Updated 2 weeks ago

w2n/deepseek-v4-flash

tools

173 Pulls 1 Tag Updated 3 weeks ago

pdurugyan/qwen3.5-9b-deepseek-v4-flash-Q4_K_M-v_2

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 +

vision tools thinking

6,017 Pulls 1 Tag Updated 3 months ago

ZimaBlueAI/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

tools thinking

3,627 Pulls 1 Tag Updated 3 months ago

pdurugyan/qwen3.5-9b-deepseek-v4-flash-Q4_K_M

Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4.

tools thinking

2,435 Pulls 1 Tag Updated 3 months ago

frob/deepseek-v4-flash

0731

tools thinking 284b

1,053 Pulls 17 Tags Updated 2 weeks ago

kenevo/DeepSeek-V4-Flash-UD-Q4_K_XL

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

rafw007/deepseek-v4-flash-fast

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