Inkling-2-Mini From Thinking Machines Spotted With Full vLLM Serve Command
TheZachMueller · x · 2026-11-22
A notable sighting: the poster shares a complete vLLM command for serving thinkingmachines/Inkling-2-Mini, suggesting Thinking Machines (Mira Murati's lab) has released/uploaded the model weights.
Reusable config details:
- 262144 max context length, gpu-memory-utilization 0.9
- Dedicated --reasoning-parser inkling and --tool-call-parser inkling with --enable-auto-tool-choice
- Speculative decoding: method dspark, numspeculativetokens 7, draftsamplemethod probabilistic
A ready-to-use deployment reference for anyone wanting to run the new model locally on day one.
More from Infra
- Metal NVFP4/MXFP8 Kernels Cut Inkling 2 Mini Memory from 46.2GiB to 9.9GiB on M3 Max — GabGarrett · 2026-11-22
- Training compute cost per task may be mere cents, argues 1a3orn — if models generalize from small runs — 1a3orn · 2026-11-22
- Miners 'hacked' Chutes for a year with millions in incentives to forge real end-to-end TEE privacy — const_reborn · 2026-11-22
- lxask: a fine-tuned 1.5B model turns plain English into offline Linux commands, self-checked against man pages — Arch-r007 · 2026-11-22
- Second OpenRouter Leak in a Month: MiniMax-Route Prompts May Have Been Read — const_reborn · 2026-11-22
- capy-flash v0.16 runs Inkling 2 Mini on two 16GB GPUs at 149 tok/s with 254k context in NVFP4 — FeydRowan · 2026-11-22