First steps for a specialized DeepSeek v4 Flash inference... engine focused on inference quality / stability at different quantizations, with networked API that is batching capable. This is the 2 bit quants model running on my M3 Max 128GB.show more

DeepSeek V4 Flash 0731 first test. DeepSeek V4 Flash... 0731 is ridiculously cheap compared to Kimi K3, GPT-5.6, and Opus 5 For its price, this is a surprisingly capable model. First challenge: Generate a railway station in Three.js. The result exceeded my expectations for such a low-cost model. It’s definitely one to watch if you’re building 3D projects on a tight budget.show more

MAI-Code-1.1-Flash is going local with on-device model calls inside... Github Copilot. High-quality agentic coding on your device, with no inference charge for local model calls.show more

DeepSeek DeepSeek is now live on Heurist. Open source... AI just reached new heights. Access DeepSeek-R1 and DeepSeek-V3 for smarter inference at a fraction of cost. Try it via Heurist API or explore on Pondera.show more

Got DeepSeek V4 Flash running on 2x H200s at... 160–200 tok/s on JarvisLabsAI this speed is perfect for in the loop things I do with these agents. It feels like a GLM-5.2-class model with much lower hardware requirements. I’m going to daily-drive it for a bit and see how it performs, but first impressions are really good.show more

this is the best trick to maximum usage limits... on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)show more

deepseek v4 pro is basically free right now 😳... teamorouter is offering deepseek v4 pro at almost no cost you can also use deepseek v4 flash for free what you get: - deepseek v4 pro free - deepseek v4 flash free - 1M context - openai compatible api - no subscription - credits never expire why this is worth checking: > v4 pro is currently listed at $0 input and output > flash is also available at $0 > works with claude code, codex and other tools > one api gives you access to multiple models getting started: 1. go to 2. create your account 3. open the dashboard 4. create your api key base url: 5. add it to your ai coding tool 6. select deepseek-v4-pro-free worth testing while it’s availableshow more

Running DeepSeek R1 on my desk Uses EXO Labs... with Thunderbolt 5 interconnect (80Gbps) to run the full (671B, 8-bit) DeepSeek R1 distributed across 2 M3 Ultra 512GB Mac Studios (1TB total Unified Memory). Runs at 11 tok/sec. Theoretical max is ~20 tok/sec.show more

AGI at home Running DeepSeek R1 across my 7... M4 Pro Mac Minis and 1 M4 Max MacBook Pro. Total unified memory = 496GB. Uses EXO Labs distributed inference with 4-bit quantization. Next goal is fp8 (requires >700GB)show more

Nemotron 3 Ultra is fast and genuinely good Compared... it with 3 frontier models: DeepSeek V4, MiniMax M3, and Qwen 3.7 Max on 2 prompts very impressive resultsshow more

free access to 8+ top AI models 😳 APInex... is offering free models with 1M context - Gemini 3.8 Flash - Muse Spark 1.3 - GLM 5.3 Flash - Gemini 3.1 Pro - DeepSeek V4 Pro - GPT-5.6 Luna - Qwen 3.8 MAX - DeepSeek V4 Flash getting started: 1. go to 2. sign up with Gmail 3. create your API key 4. base url 5. choose a free model and start using free models, one API setup 👀show more

Batching for vision models is now available in Beta... with our latest MLX engine update 👾 The updated engine also brings major improvements to caching for faster inference overall. Turn on Developer Mode, choose the beta runtime channel, and select LM Studio MLX v1.8.1.show more

Deepseek-v4-Flash running locally. Makes me dizzy, this is one... of 6 sessions running rnshow more

Watching llama.cpp do 40 tok/s inference of the 7B... model on my M2 Max, with 0% CPU usage, and using all 38 GPU cores. Congratulations Georgi Gerganov ! This is a triumph.show more

STOP PAYING FOR APIS RIGHT NOW MASSIVE DROP ON... APINEX😳 8 elite models 100% FREE to milk right now: -gemini 3.8 Flash -muse Spark 1.3 -GLM-5.3 Flash -gemini 3.1 Pro -deepseek V4 Flash -deepseek V4 Pro -GPT-5.6 Luna -qwen 3.8 MAX chose your free model register here: https:// get your api key: save this post before it disappearsshow more

How much faster is the new MacBook Pro for... AI inference? M4 Max is 27% faster with 72 tok/sec compared to 56 tok/sec of the M3 Max with MLX running Gemma 2 9B (4bit). The 27% speedup is the same with Llama-3.2-1b, Llama-3.2-3b and others. Next up: EXO Labs M4 cluster.show more

DeepSeek v4 Flash has 43 blocks... so, even 4096... batches during the prefill can be smoothly visualized. Look at the new progress bar.show more

DeepSeek V4 Flash 0731 is now available on Venice,... fully private.show more

Happy Friday! We just put DeepSeek-V4-Pro up on It’s... the world’s largest open source model at 1.6T parameters, and you can run it for free running on NVIDIA Blackwell GPUs. Try the NVIDIA NIM API →show more

DeepSeek V4.1 Flash just got a serious upgrade. DeepSeek’s... 1017 outscores leading open-source and frontier models on nearly every benchmark. Same model in the Venice app, simply upgraded and available via the API as deepseek-v4-1-flash-1017. Fully private.show more

QWEN 3.8 MAX + DEEPSEEK V4 PRO BOTH FREE... ON ONE ENDPOINT • the gateway > Qwen3.8-Max (2.4T MoE) + DeepSeek V4 Pro free tiers: > Sign up -> one API key -> start with no card for free tier. > Free is tight by design -- they’re letting you taste the real thing before you scale. • wiring it up > Base url: >Model IDs exact: qwen/qwen3.8-max-free and deepseek/deepseek-v4-pro-0813-free. > Drop straight into Cursor/Claude Code/any OpenAI-compatible client. Good for long agent runs you leave open on a second screen, slow for anything interactive. Point it at side projects and experiments, not at the code you would mind a stranger reading ↓show more