DingoOz/llm-visuals
Live truecolor terminal dashboard for a locally running LLM: tok/s, TTFT, GPUs, context, MTP acceptance, layer and real expert routing (llama.cpp)
About the project
Live terminal dashboard for a locally running LLM: shows tok/s, TTFT, GPU load, context fill, speculative-decoding acceptance and MoE expert routing (llama.cpp).
Useful for
- Watch tok/s and TTFT during a request to llama-server
- Check GPU load and memory while a model loads via nvidia-smi
- See which experts a MoE model routed the last token through
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 4 stars so far today, about 6 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 7 days old and already has 77 stars.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 77
- Stars in a day
- 6
- Forks
- 11
- Issues and pull requests
- 5
- Watchers
- 1
- Language
- Rust
- License
- MIT
- Latest release
- v0.8.1 · September 18, 2026
- Created
- September 11, 2026
- Last push
- September 18, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 17, 2026Top new repositories this week: #156
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/DingoOz/llm-visuals)Similar projects
-
8.6
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.
-
7.1
vinnylarouge/jevlike
A small trainable model that picks one option from a changing list of text options in a single forward pass, an open alternative to TypeSafe's Jev. Aimed at developers who need fast classification or menu selection…
-
6.9
Continuum-AI-Corp/OrcaBonsai-27B-Uncensored
A tool for runtime refusal ablation in the compressed Ternary Bonsai 2 27B LLM: it projects the residual stream to remove the refusal direction without modifying or re-quantizing weights. Runs on Apple Silicon via MLX.
-
6.4
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).
-
6.3
zhengkid/Dream-RSI
Research project on recursive self-improvement: past discovery histories become a replay simulator used to evaluate and refine exploration policies. Code is still being prepared; paper and demo are available.
-
5.0
ekzhang/openjev-sglang
HTTP server implementing the TypeSafe/Jev API for structured text classification on Qwen3.6-35B-A3B via SGLang; returns answer probabilities without generating a chain of thought.