deepseek-v4 repositories
Trending repositories tagged deepseek-v4, ranked by trending score. Updated daily.
-
1
FlashML-org/FreeToken
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
GitHub · Python · 17,582 stars · 1,748 forks · +252 stars in 24 hours · Trending score 4.33
-
2
ddalcu/mlx-serve
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
GitHub · Zig · 2,554 stars · 275 forks · +54 stars in 24 hours · Trending score 3.14
-
3
sums001/Deepseek-API
Reverse engineered Deepseek chat into an OpenAI compatible API. Access V4 and R1 models through a simple REST interface without API keys or billing.
GitHub · Python · 381 stars · 98 forks · +55 stars in 24 hours · Trending score 3.06
-
4
synchopate/llama-modchip
Zero-GPU CPU inference for 30B-284B MoE models (Qwen3.8 176.5B cold-cache certified in 28.26/48.35 GiB Cgroup v2, DeepSeek-V4 284B, Nemotron-30B) + RouteCrack 2.0.
GitHub · Python · 1,399 stars · 137 forks · +19 stars in 24 hours · Trending score 3.00
-
5
snake-aabb-wtf/deepseek-web2api-free
基于 FastAPI 的 DeepSeek Chat 反向代理,将 DeepSeek 网页版的 API 转换为 OpenAI 兼容格式。 支持流式/非流式对话、专家模式、深度思考(reasoning_content)、工具调用(DSML prompt injection)。 自动处理 PoW 鉴权挑战,无需官方 API Key。
GitHub · Python · 225 stars · 58 forks · +34 stars in 24 hours · Trending score 2.65
-
6
bertholomus/deepseek-v4.1-tensorfold-tp2-2xgb10
BertholomusAI recipe: DeepSeek-V4.1-Flash-1017 on 2x NVIDIA DGX Spark (GB10), our own TensorFold TP2 engine. Weights: bertholomus EXL3 2.5bpw quant (MIT). v0.7.5.
GitHub · Python · 73 stars · 7 forks · +33 stars in 24 hours · Trending score 2.64
-
7
Indras-Mirror/Xolotl
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s agent, ~41 fast, 512K context. Plus Inkling-2-Mini (Thinking Machines, own engine + MTP drafter), GLM-5.3-Flash, Qwen3.8, LFM3-Omni. MoE experts tiered across VRAM, RAM and NVMe (Xolotl Direct). OpenAI + Anthropic API.
GitHub · C++ · 554 stars · 69 forks · +15 stars in 24 hours · Trending score 2.31
-
8
B3hnamR/Polygate
A free model gateway for Windows and Linux with WARP, proxy pool and Relay. With Unlimited use of OpenCode and Kilo
GitHub · TypeScript · 34 stars · 7 forks · +9 stars in 24 hours · Trending score 1.85
-
9
NVIDIA-NeMo/Automodel
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
GitHub · Python · 1,098 stars · 391 forks · +5 stars in 24 hours · Trending score 1.75
-
10
Magnvs7/Promethevs
PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-correct), OpenAI-compatible local server, report and logs.
GitHub · 193 stars · 13 forks · +2 stars in 24 hours · Trending score 1.30
-
11
hanxiao/DeepSeek-V4.1-Flash-1017-FP8-abliterated-4x-RTX-PRO-6000
Abliterated DeepSeek-V4.1-Flash-1017 (FP8 dense, FP4 experts) on 4x RTX PRO 6000 with vLLM-Moet r21, DSpark + FLy verification and top_p 1.0: 463 tok/s single-stream agent decode at 30k-120k context, 1082 tok/s over 8 streams, 1M context, Flex-start GCE VM
GitHub · Python · 62 stars · 11 forks · +5 stars in 24 hours · Trending score 1.30
-
12
Microqian2th/dsh-codex-effort-slider
Codex 风格的推理等级滑条(DeepSeek Harness 插件):可拖动连续滑条 + 高档位渐变星尘特效
GitHub · JavaScript · 284 stars · 17 forks · 0 stars in 24 hours · Trending score 1.07
-
13
atharvotech/FreeDeepseekAPI-EN
Local OpenAI-compatible API proxy for DeepSeek Web Chat (Global English Version). Connects DeepSeek to Open WebUI, Claude Code, and OpenAI SDK tools. Maintained by Atharvotech.
GitHub · JavaScript · 97 stars · 12 forks · 0 stars in 24 hours · Trending score 1.05
-
14
countbot-ai/CountBot
Lightweight open-source AI Agent hub | 轻量多用户开源AI Agent,多租户隔离,原生DeepSeek,多IM接入
GitHub · Python · 786 stars · 103 forks · +3 stars in 24 hours · Trending score 1.00
-
15
htmsty/autoThuDeepSeekAPI
自动获取清华大学 MadModel 平台(https://madmodel.cs.tsinghua.edu.cn/)的 API Token, 并写入 DeepSeek Harness(DSH)与 CC Switch 的配置。Windows 便携程序,双击即用。
GitHub · Python · 12 stars · 0 forks · +3 stars in 24 hours · Trending score 0.93
-
16
1eakkkk/liuyao-tool
六爻排盘 + AI 解卦,基于火珠林纳甲法,网页/安卓/Windows 三端,打开即用
GitHub · JavaScript · 15 stars · 4 forks · +2 stars in 24 hours · Trending score 0.90
-
17
jiiim/ds-menu-bar
DS Menu Bar - A Lightweight Menu Bar Control for DwarfStar Server (ds4-server)
GitHub · Swift · 18 stars · 6 forks · +2 stars in 24 hours · Trending score 0.82
-
18
SimonMedy/DSH-Mobile
Unofficial community mobile client for the DeepSeek Harness Web UI.
GitHub · TypeScript · 22 stars · 0 forks · +2 stars in 24 hours · Trending score 0.79
-
19
fish2lab/DSCodex
在原版 ChatGPT / Codex 同时使用 DeepSeek V4.1 Flash 与 GPT。Local loopback router, native Responses API, full tool loops, no fork.
GitHub · JavaScript · 54 stars · 16 forks · 0 stars in 24 hours · Trending score 0.64
-
20
SnowLLM/SnowLLM
Your Ryzen AI Max is running at half speed. SnowLLM: up to 9x faster prefill and 2x faster decode than llama.cpp on the same GGUF. Qwen3.6-35B-A3B, Qwen3.8-Flash-Next, DeepSeek-V4-Flash.
GitHub · Python · 21 stars · 2 forks · 0 stars in 24 hours · Trending score 0.56
-
21
konglong87/free-AI-free-token
free-AI-free-token,免费token集中营。免费API-Key|多模态|视频|图片|文本|
GitHub · Shell · 23 stars · 3 forks · 0 stars in 24 hours · Trending score 0.53
-
22
Drobiazkin/agent-gpu-calculator
Single-file GPU/RAM sizing calculator for LLM agent sessions on vLLM: KV-cache offload to RAM, prefix caching, MLA/DSA and hybrid models, TP chosen per model × GPU pair (H100–B300). Runs in the browser, no dependencies.
GitHub · HTML · 9 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46
-
23
snake-aabb-wtf/skill-webAI2api
输入任意 AI 聊天网页的 URL + Cookie,全自动逆向分析其私有 API,生成 OpenAI 兼容的代理服务器。支持流式输出、DSML 工具调用、PoW 自动求解。
GitHub · Python · 36 stars · 7 forks · +1 stars in 24 hours · Trending score 0.45
-
24
TimeMachineLab/awesome-deepseek-harness-zh
DeepSeek Harness 中文使用指南与资源大全:dsh 安装教程、模型与 API Key 配置、插件、Skills、MCP、报错排查
GitHub · Python · 25 stars · 2 forks · 0 stars in 24 hours · Trending score 0.43