Leading general-purpose foundation models & professional AI agents. The proprietary Spark model family, with AStudio & Loomy harnesses. Open source.
Joined August 2026
- Tweets186
- Following27
- Followers2.2K
- Likes288
A full day. A blank diary.
Karl-XZ’s Blackbox Diary uses Spark-X2.5-4B on Android to turn saved material into a daily summary. The screenshot uses 12 synthetic notes—not a real user diary.
github.com/Karl-XZ/blackbox-…
1
8
417
You also choose what stays.
Voiceprint enrollment is optional; matching is tentative, not identity authentication. The deletion screenshot shows a date-range dialog only—no deletion was performed during capture.
1
1
56
Author release checks: 45 core software tests passed. That is not model accuracy. Long-run stability, battery use and human factual review remain unverified.
Android 14+; v1.3.2 prerelease debug APK. Model import required:
github.com/Karl-XZ/blackbox-…
1
65
Same A40. Same Spark-X2.6-4B file. A new CUDA path.
infosave reports 111.5 vs 80.2 tok/s after 4k tokens (4-bit, CUDA vs Vulkan). At 64k: 100.7 tok/s, 42.3s to first token, 8.2GB peak VRAM. Author tests; charts below.
huggingface.co/XHToken/Spark…
2
24
1,075
The CPU chart stays in the story too: llama.cpp is faster in some tested conditions. Turbo runs as the standard file on CPU. Choose a backend for your actual device and document, then measure waiting time and answer quality as well as tok/s.
1
1
89
Try cortiq 0.8.67+ built with --features cuda and CUDA 12.x runtime libraries. This backend is experimental, tested on one A40, and has no speculative decoding. Original charts and setup by infosave:
huggingface.co/XHToken/Spark…
1
83
No discrete GPU. A Raspberry Pi 5. What can local AI do?
ai-tier reports Spark-X2.5-1.7B Q4_K_M at 10.5 tokens/s on a 16GB Pi 5.
4,096 context, reasoning off; short-input test. Third-party results, not our rerun.
4
10
645
The memory result: 2,378 MiB peak, including the model and excluding other apps.
That is a measurement on a 16GB Pi, not proof that a 2GB Pi will work. Longer inputs may need more memory.
1
2
154
Speed is only part of the story: the response test reports 8.4s to first text and 34.5s task time.
Measured October 19, 2026 (UTC). Bring your own task and measure the wait, too.
ai-tier.com/results/raspberr…
3
91
A model release is only the beginning.
276 community derivatives later, Spark X2.5 + X2.6 have passed 5M downloads/pulls across six platforms.
Thank you for making Spark your own. 💜
huggingface.co/XHToken
The community now accounts for 57.1% of the tracked total:
Official channels: ~2,189,056
Community derivatives: 2,912,337
HF official + derivatives alone: 5,050,020
From GGUF to MLX and ONNX, open weights become more ways to build.
1
1
402
Small models. More possibilities.
Explore Spark 4B / 1.7B, pick a format, and show us what you build:
github.com/XHToken/Spark-X2.…
Snapshot: Nov 8, 2026 UTC. Totals include pulls and approximate counts; platform methods differ. Not unique users.
250
The weaker outputs belong in the story: logo fidelity 0.219; bottle 0.393. That measures agreement on size, proportions and part count, not beauty.
Only 20/50 scripts built geometry on 3DCode. Specialization still has limits.
1
2
133
Credit: hotocooo, using Spark-X2.6-4B-Base. Original renders preserved; data/layout cards by SparkLLM. We have not rerun the tests.
Try the author's completion prompt and share what you build:
huggingface.co/hotocooo/Spar…
2
116