deepseek v4.1 flash · Ollama

Any Local Cloud

Capabilities

Tools Thinking Vision Embedding Decision

Download size

deepseek-v4.1-flash
2w

visiontoolsthinking cloud

Designed for greater capability, faster inference, higher throughput, and scaling to larger models.

1M $$$$
wob_rotson/deepseek-fixed
15h

toolsthinking

A reset version of Eriktonon's DeepSeekv4.1-Flash - Ready for use in AI Agent Scenarios

6
eriktonon/deepseek-v4.1-flash-1017
1w

toolsthinking

UNCENSORED (Abliterated + SecOps) — DeepSeek-V4.1-Flash-1017 (9B Compact & 27B Large 128K Edition) — Fine-tuned & Orthogonally Abliterated for Agents Architecture, Rust Systems & Autonomous Tool-Use.

5,507 3 tags 9b 27b
frob/deepseek-v4.1-flash
6d

vision

1017

222 5 tags 552b
shuiyuPyLab/deepseek-v4.1-flash-super-extreme-quant
3w

98
stepanchuvashov1987/deepseek
3w

tools

deepseek-v4.1-flash:cloud

69
alturisabdulrahman/deepseek-v4.1-flash
1mo

tools

344
kck4156/deepseek-v4.1-flash
1mo

cloud
heuristic_gates_109/deepseek-v4.1-flash-opencode
1mo

cloud

Fork of igovet / deepseek-v4-flash-new-opencode but based off deepseek-v4.1-flash
kenevo/DeepSeek-V4-Flash-UD-IQ1_S
3mo

To run DeepSeek-V4-Flash in full precision lossless, run IQ1 (UD-IQ1_S), It is 82GB. vision tools thinking

460
bluehawana/deepseek-v4-flash
2mo

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.

1,320