TokenMark
TokenMark is Daily-tracked model releases and real tok/s benchmark configs for large-unified-memory home AI rigs, AMD Strix Halo (Ryzen AI Max+ 395) and NVIDIA DGX Spark (GB10). One searchable, source-linked leaderboard.. It is ranked #1616 on the AI Radar, in AI infra & evals, first seen 1 h ago and shared in 1 post (13 views).
TokenMark: Local AI Config Tracker for Strix Halo & DGX Spark TokenMark: Local AI Config Tracker for Strix Halo & DGX Spark Daily-tracked model releases and real tok/s benchmark configs for large-unified-memory home AI rigs, AMD Strix Halo (Ryzen AI Max+ 395) and NVIDIA DGX Spark (GB10). One searchable, source-linked leaderboard. Snapshot 2026-09-21 · 211 configs · 94 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand. AMD Strix Halo (Ryzen AI Max+ 395) · 147 single-stream configs Model Quant Backend Decode Context Trust Source Qwen3 0.6B Q8_0 llama.cpp/vulkan 266…
What people said about TokenMark on X
Two boxes, same Gemma 4 12B QAT, 3 percent apart. Meanwhile one alias on one box billed 416 tokens for a prompt, then 548 for the identical retry. Temp 0. Ran the non-reasoning alias as a control, same drill: 10 completion tokens, twice, zero variance. It even reports cache hits, 13 then 25 of 26 prompt tokens…
— @cozybearlog, 1 h ago · 0 likes · see the post
Alternatives to TokenMark
- StepFun Open Platform — Step API · Stable · High-Performance · Easy Integration. Leading models and tools to accelerate the deployment of your…
- classifier.dev — now outperforms jev and is free
- glm-5.3-flash-exl3-2x-dgx-sparks — GLM-5.3 Flash EXL3 for 2-4x DGX Sparks. Contribute to MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks development by…
- Jev API, Pricing & Playground — Jev is now available on the @vercel AI Gateway
- halo — Star us on GitHub
- glm-5.3-flash-nvfp4-1m-kv-4x-dgx-spark — GLM-5.3-Flash (320B MoE) at TP4 across four DGX Sparks, same day as the model drop: 36 tok/s, 1.26M-token FP8 KV pool,…
TokenMark in numbers
- Rank on the AI Radar: #1616 of 1703
- Shared in 1 post by 1 account: @cozybearlog
- 13 views on those posts
- First seen 1 h ago, last shared 1 h ago
- Pricing seen by Jev: not stated
- Market: AI infra & evals
FAQ
What is TokenMark?
Daily-tracked model releases and real tok/s benchmark configs for large-unified-memory home AI rigs, AMD Strix Halo (Ryzen AI Max+ 395) and NVIDIA DGX Spark (GB10). One searchable, source-linked leaderboard. It was first shared on X 1 h ago and is ranked #1616 on the AI Radar.
Is TokenMark free?
Pricing is not stated on the page we read.
Who shared TokenMark?
1 account on X, including @cozybearlog, in 1 post totalling 13 views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 41k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 04:47 UTC. Full method.