11 entries
Keyword: deepseek-v4Repository:JustVugg/colibri
Colibrì is a lightweight inference engine written in pure C with zero dependencies, designed to run frontier Mixture-of-Experts (MoE) models ranging from 744B to 2.8T parameters on consumer and heterogeneous hardware. It treats VRAM, RAM, and storage as a unified memory hierarchy, streaming experts on demand.
37.7kstarsC
From X post: Ten Open-Source Repositories Powering AI Agent Infrastructure
Repository:MiaAI-Lab/DeepSeek-v4-Flash-One-DGX-Spark
An open-source launcher and Docker recipe for running DeepSeek V4 Flash 0731 (EXL3) on a single NVIDIA DGX Spark with 128 GiB unified memory.
328starsPython
From X post: Running DeepSeek v4 Flash on a Single NVIDIA DGX Spark
Article:Nemo, DGX Spark & Local Inference Engineer
A local benchmark test running Qwen3.8-Flash-Next NVFP4 on a single NVIDIA DGX Spark (GB10) achieved 87.3% on smf-bench Official A, outperforming a previous dual-Spark DeepSeek V4 setup in quality.
From X post: Qwen3.8-Flash-Next on a Single NVIDIA DGX Spark Outscores Dual-Spark Setup in Benchmark
Repository:unslothai/unsloth
Unsloth is an open-source cross-platform desktop application and framework designed to run and fine-tune large language models and diffusion architectures locally across varied hardware setups.
75.7kstarsPython
From Video: AI Weekly Updates: Open-Source Model Surge, Agent Harnesses, and Meta's AI Reality Check
Repository:FlashML-org/FreeToken
FreeToken is an open-source inference engine designed to run massive Mixture-of-Experts (MoE) models on desktop PCs and laptops. Using adaptive CPU-GPU co-execution, semantic caching, and dynamic VRAM management, it enables models like DeepSeek-V4-Flash and GLM-5.2 to run locally without datacentre infrastructure.
11.7kstarsPython
From Video: AI Weekly Updates: Open-Source Model Surge, Agent Harnesses, and Meta's AI Reality Check
Link:deepseek-ai
DeepSeek-AI has officially released DeepSeek-V4-Flash-0731 on Hugging Face. The 304B-parameter model supersedes the preview version, featuring integrated DSpark speculative decoding and significantly enhanced agentic performance.
From Video: Weekly AI Updates: Local Models, GPT-6 Astra, and Agent Architectures
Link:deepseek-ai
DeepSeek-V4-Flash-0731 is a sparse Mixture-of-Experts language model featuring 13B active parameters and a 1-million-token context window. The NVIDIA Build model card outlines technical specifications, architecture details, and coding benchmark performances.
From Video: Weekly AI Updates: Local Models, GPT-6 Astra, and Agent Architectures
Link:Unsloth AI
Unsloth provides an open-source framework and desktop application to run and train AI models locally. With the 'unsloth start' feature, coding agents such as Claude Code and Codex can directly connect to local models.
From Video: Weekly AI Roundup: DeepSeek Harness, Model Routing, and Scaffolding Shifts
Article:Simon Willison
DeepSeek has introduced DeepSeek-V4-Pro and DeepSeek-V4-Flash under an MIT licence. Simon Willison reviews their Mixture of Experts architecture, KV cache efficiency gains, and pricing compared to OpenAI, Google, and Anthropic.
From Video: Weekly AI Updates: Model Releases, Agent Harnesses, and Developer Tooling (August 2026)
Article:DeepSeek AI
DeepSeek has open-sourced the preview release of DeepSeek-V4. The line-up features DeepSeek-V4-Pro and DeepSeek-V4-Flash, standardising a 1M context window and introducing architectural innovations to cut compute and memory overhead.
From Video: Weekly AI Updates: Model Releases, Agent Harnesses, and Developer Tooling (August 2026)
Link:deepseek-ai
DeepSeek has published the model card and weights for DeepSeek-V4-Pro-DSpark on Hugging Face. The release equips the DeepSeek-V4-Pro MoE model with an attached speculative decoding module (DSpark) for accelerated inference.
From Video: Weekly AI Updates: GPT 5.6, Claude Sonnet 5, and Ornith
11 of 11 shown
Do you have an interesting article, a video, or a tweet that belongs in our knowledge base? Write to us at office@webconsulting.at.
Parts of this content were created with the assistance of AI.
