Author: Tater Totterson

Ollama – v0.13.4-rc2

🚀 Ollama v0.13.4-rc2 just dropped—and it’s all about speed and stability!

If you’ve ever sat there watching “Loading model…” like it’s a slow-loading game, this update is your cheat code.

✨ What’s new:

• ⚡ Faster model init — Memory mapping + CUDA context tweaks slash startup time.
• 🤖 Multi-GPU love — Better resource splitting so your 2x or 4x GPUs actually work together, not fight.
• 🛠️ Smarter cache — Fewer crashes from corrupted downloads or interrupted pulls.

💡 Pro tip: Running Llama 3 or Mistral on a multi-GPU rig? You could see 20%+ faster load times.

Still a release candidate—but if you’re ready to cut the wait time and boost reliability, upgrade now. Your GPU’s doing backflips in gratitude. 🤖💻

🔗 View Release

Deep-Live-Cam – 2.4

Deep-Live-Cam 2.4 just dropped—and it’s a game-changer for real-time face swaps 🎭💻

✅ Dropdowns fixed — No more menu stutters. Smooth sailing through all your deepfake edits.

⚡ Forced GPU mode on laptops — Finally, your iGPU won’t hold you back. Full CUDA/CoreML/DirectML power unlocked.

🎨 Poisson Blending upgraded — Translucent artifacts? Vanished. Messy ear edges? Gone. Swaps now look planted, not pasted.

👄 Mouthmask optimized for Inswapper — Lips sync perfectly with speech. No more robot-smiles. Realistic expressions, zero effort.

Plus tiny but massive polish tweaks—because your deepfake shouldn’t have glitches.

All updates live only on the official site. Grab it before your GPU starts sending you love letters 💬🔥

🔗 View Release

Text Generation Webui – v3.21

🚀 Text Generation WebUI v3.21 just dropped — and it’s lighter, faster, smarter!

The portable builds are now leaner: no more bloated llama.cpp symlinks (Python .whl quirks, we see you 😅). They auto-recreate on first launch — clean, efficient, zero hassle.

🔥 Backend upgrades galore:

• llama.cpp → updated to latest ggml-org commit (5c8a717) — smoother inference, fewer crashes
• ExLlamaV3 v0.0.18 — better quantization + smarter memory use
• safetensors v0.7 — faster load times, tighter security
• triton-windows 3.5.1.post22 — CUDA ops on Windows? Smoother than ever

📦 Portable builds now come in 4 flavors:

• 🖥️ `cuda12.4` (NVIDIA)
• 💻 `vulkan` (AMD/Intel GPUs)
• 🧠 `cpu` (no GPU? no problem)
• 🍏 `macos-arm64` (Apple Silicon optimized)

🔄 Update? Just unzip → replace only your `user_data/` folder. All your models, settings, themes — untouched. No reconfiguring. No stress.

Perfect for tinkerers who want power without the install drama. Grab it, unzip, and start generating 🚀

🔗 View Release

Ollama – v0.13.4-rc1

🚀 Ollama v0.13.4-rc1 just dropped — and Gemma 3 just got a serious upgrade!

Gemma 3’s RoPE scaling is now set to 1.0, meaning:

✅ Better long-context handling

✅ Fewer hallucinations

✅ More stable reasoning on laptops and low-resource rigs

Perfect for RAG apps, chatbots, or code assistants that need to stay sharp on long prompts.

Under the hood:

🔧 Smoother model loading

🧠 Minor memory optimizations

⚡ Improved compatibility with newer GPU drivers

This is a release candidate — stable, tested, and ready for early adopters who want to ride the wave before it hits mainline.

Grab it, tweak your prompts, and start gemma-ing harder 🤖✨

🔗 View Release

Ollama – v0.13.4-rc0

🚀 Ollama v0.13.4-rc0 is live — and it’s a game-changer for Gemma 3 users!

Fixed: Global RoPE scale values are now properly applied, meaning longer prompts get way more accurate reasoning and smoother context handling. No more weird token scaling glitches — your Gemma 3 finally behaves like it should.

✅ Verified release (GitHub-signed for trust & security)

✅ Smoother, more consistent inference across macOS, Windows, and Linux

If you’re running Gemma 3 locally? Update now. This isn’t just a patch — it’s your model finally unlocking its full potential. 🤖✨

Grab it before the final drops — and keep those LLMs running clean!

🔗 View Release

Mantella – v0.14 Preview 1

Hey AI tinkerers! 🚀

Mantella v0.14_preview_1 just dropped — and it’s turning Skyrim and Fallout 4 NPCs into living, breathing conversationalists.

• 🗣️ Auto greetings in group chats — NPCs now start convos when someone new walks in. No more awkward silences.
• 💬 First sentence always speaks — even if you interrupt mid-sentence. Dialogue flows like real life.
• 🚫 Fast responses disabled in radiant dialogue — less spam, more soul. Perfect for immersive storytelling.
• 🎮 New advanced actions — trigger NPCs based on proximity, state, or events. Build smarter worlds.
• ⚙️ Standalone LLM framework for function calling — cleaner, more powerful logic behind the scenes.
• Italics now parse correctly — emphasis and lore-heavy lines? Done right.
• 📅 Day tracking in prompts — NPCs remember how long you’ve been gone. World feels alive.
• 🔧 All tool parameters exposed — no black boxes. Tinker to your heart’s content.

This isn’t just an update—it’s the future of in-game dialogue. Go make NPCs that feel real. 🌟

🔗 View Release

Ollama – v0.13.3: Update README.md (#13373)

Ollama v0.13.3 just dropped — tiny update, big win for docs lovers! 📚✨

The team fixed a few broken links in the README:

• Swollama (community tool) → now points to the right place
• DocC docs → no more 404s, just clean access to docs

No new models. No API tweaks. Just flawless documentation so you can dive in without hitting dead ends.

Perfect for tinkerers who appreciate polish — because clean docs = faster experimentation. 🛠️

Keep running LLMs like a pro!

🔗 View Release

Lemonade – v9.1.0

🚨 Lemonade v9.1.0 is LIVE — your local LLM powerhouse just got a major upgrade! 🍋

The brand-new Lemonade App (Windows .msi / Linux .deb) replaces the old browser UI with a sleek native experience. Here’s what’s fresh:

• 🎙️ ASR via whisper.cpp — transcribe audio right inside the app (toggle with env vars!)
• 📥 Built-in Model Downloader — no more terminal commands to grab GGUF/ONNX models
• 🔄 Switch LLMs & FLMs on the fly — test FLM2-1.2B-FLM with improved reasoning logic
• 📏 Smart Model Manager — filters by RAM usage so you don’t crash your system
• 🌐 Server now defaults to IPv4 — goodbye, localhost confusion

Under the hood:

• 🐳 Official Docker/CMake dev setup
• 💬 Chat UI now shows FLM “thinking” in collapsible boxes
• 📚 Debate Arena docs live + Jan model fix shipped
• 💥 All-in-one installer: app + server bundled. Minimal server still available for headless use

Pro tip: Click the model dropdown — it actually loads models now. And yes, you can collapse thinking by default.

Shoutout to @danielholanda, @jeremyfowers, and @Geramy — you’ve built something wild.

Download. Play. Break it. Fix it. Repeat. 😎

🔗 View Release

Ollama – v0.13.3-rc1: feat: llama.cpp bump (17f7f4) for SSM performance improvements (#13408)

🚀 Ollama v0.13.3-rc1 is live — and Apple Silicon users, this one’s for you!

llama.cpp just got a massive upgrade to latest master (17f7f4b), turbocharging SSM models like Granite-4, Jamba, Falcon-H, Nemotron-H, and Qwen3 Next on Metal.

💥 What’s new?

• Prefill speed up by 2–4x on M1/M2/M3 — fewer waits, faster first tokens
• Optimized `SSM_CONV` and `SSM_SCAN` ops — the secret sauce behind modern state-space models
• Clean swap to `gemma3.cpp` (goodbye, -iswa!)
• 30+ patches + vendored code sync for stability

If you’re running SSMs on Mac — upgrade now. Your chat latency just got a serious caffeine boost. 🍏⚡

🔗 View Release

Heretic – v1.1.0

Heretic v1.1.0 just dropped—and it’s a game-changer 🚀

Apple Silicon support? ✅ Run decensoring natively on your M-series Mac.

IBM Granite MoE now supported? ✅ Unlock massive efficiency with MoE models.

Multi-GPU? ✅ Split the load like a pro—no more GPU bottlenecks.

MXFP4 + Triton tensors? ✅ Leaner, faster inference on compatible hardware.

Local datasets and `trust_remote_code`? Smooth sailing now.

Colab/Kaggle compatibility? ✅ Drop it in your notebook and go.

Float32 bugs fixed? ✅ No more precision surprises.

Refusal detection got smarter—better at spotting those “I can’t help” vibes.

Early stopping, thinking models, padding fixes? All there for the tinkerers.

And yes—CI now lints PR titles because clean commits = happy devs 😎

8 new contributors joined the crew. Welcome!

Upgrade. Decensor. Unleash. 💥

AGPL-3.0 | PyTorch 2.2+ | RTX 3090? ~45min for 8B models.

🔗 View Release