# ZONOS3-Mini, BotPsy, NVIDIA Snapshot, Seedream 5.5

> An open 100M-active speech model, a 0.8B tool-use model, GPU checkpoint and restore for Kubernetes, and Seedream 5.5 in ComfyUI.

Published 11 Nov 2026. Coverage: 10 Nov 2026 to 11 Nov 2026. By Ali Asif.

## Items

1. **ZONOS3-Mini** (Zyphra, Open weights): An Apache 2.0 text-to-speech model with 100 million active parameters, 43 languages and voice cloning, running on phones, laptops and in the browser via WebGPU. [Primary source](https://huggingface.co/Zyphra/ZONOS3-Mini)
2. **BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model** (Tether AI Research (QVAC), Agents and coding): A 0.8B model built on Qwen3.5-0.8B that roughly doubles its base on tool-use benchmarks, for example BFCL v4 from 23.4 to 44.0. [Primary source](https://huggingface.co/blog/qvac/botpsy)
3. **Start and Restore GPU Workloads in Seconds with NVIDIA Snapshot** (NVIDIA, Agents and coding): An open-source checkpoint and restore system for GPU workloads on Kubernetes that brings inference replicas online in 3.6 to 42.7 seconds, 8x to 36x faster than cold starts. [Primary source](https://developer.nvidia.com/blog/start-and-restore-gpu-workloads-in-seconds-with-nvidia-snapshot)
4. **Seedream 5.5 is now available via Partner Nodes** (ComfyUI, Image, video, world): Seedream 5.5 arrives in ComfyUI with multi-turn localized editing, native transparent RGBA output and readable in-image text. [Primary source](https://blog.comfy.org/p/seedream-55-is-now-available-via)

Four primary pages I opened today, all about making models smaller, faster to start or easier to wire into a workflow. Everything below comes from those pages, not from my own testing.

## ZONOS3-Mini

Zyphra describes ZONOS3-Mini as a compact, open-source text-to-speech model with 100 million active parameters. The weights are under Apache 2.0. It supports 43 languages, clones a voice from a short reference clip, and lets you shape age, accent and vocal texture for a designed character. Emotion, pace and delivery can be steered down to individual words.

The deployment story is what stands out. The card lists a WebGPU build that runs entirely in the browser with no server, a CUDA server, an MLX server for Apple Silicon, and a C++ ggml server that covers CPU, Metal and Vulkan. SGLang-Omni can also serve it behind an OpenAI-compatible speech endpoint with streaming. A hosted version exists on Zyphra Cloud for people who prefer that.

## BotPsy

Tether AI Research introduces BotPsy, a 0.8B model for function calling and agentic work, built on Qwen3.5-0.8B and aimed at on-device use. On the team's evaluations it roughly doubles its base: BFCL v4 goes from 23.4 to 44.0, ACEBench from 30.1 to 58.7, and tau-bench from 23.2 to 51.5. It leads five of six benchmarks even against Qwen3.5-2B-Think, a model 2.5 times its size, which still wins on Claw-Eval.

The authors are plain about limits. Multi-step information retrieval is the weak spot, performance drops as instructions pile up, and lower-resource languages lag. They say it is not meant for high-stakes use. GGUF files in bf16, Q8 and Q4 are linked.

## NVIDIA Snapshot

NVIDIA Snapshot is a new open-source component of its DSX AI Factory Platform. It captures initialized CPU and GPU memory state for a workload on Kubernetes, so a later replica restores from that artifact instead of cold starting. Across tested configurations, restores bring inference replicas online in 3.6 to 42.7 seconds, an 8x to 36x speedup over cold starts that take minutes.

It handles multi-GPU setups, including tensor, data, expert and decode context parallelism, with checkpoints up to 1 TB across eight GPUs. Checkpoint creation takes 15 seconds to 5.5 minutes, and checkpoint plus restore beats a single cold start in every tested case. These are NVIDIA's numbers on B200 GPUs with VAST NFS storage.

## Seedream 5.5 in ComfyUI

ComfyUI added Seedream 5.5 as a Partner Node, so it runs behind one node and uses credits. The post lists multi-turn editing that changes only the region you describe, native transparent and semi-transparent RGBA output, posters and infographics with readable text, and lighting control from the prompt. No benchmarks are given, so this is a feature list rather than a measured result.

## What I'd watch next

I want independent numbers for BotPsy on tasks outside its own benchmark set, and a look at how ZONOS3-Mini sounds in languages beyond English. For Snapshot, I would watch whether the restore times hold on storage other than the one NVIDIA tested.

## My take

The BotPsy numbers are the ones I would check first, since the authors compare against their own chosen set of small models and say it is weak at multi-step retrieval. ZONOS3-Mini is the release I would try first, because the weights and browser runtime are both open. I read the four pages and ran none of this myself.

## Sources

- https://huggingface.co/Zyphra/ZONOS3-Mini
- https://huggingface.co/blog/qvac/botpsy
- https://developer.nvidia.com/blog/start-and-restore-gpu-workloads-in-seconds-with-nvidia-snapshot
- https://blog.comfy.org/p/seedream-55-is-now-available-via

Canonical: https://heyaliasif.com/ai/2026-11-11-zonos3-mini-botpsy-nvidia-snapshot-seedream-5-5