RLVR on Inkling 2 Small: Beating GLM-5.3-Flash in 60 Steps for $22

Fri, 06 Nov 2026 12:00:00 +0100

RLVR field notes · Security work · November 2026

0.708 pass@1 · 12-task exploit suite

vs best GLM arm: +27 pp
Training: 60 GRPO steps
Training cost: $22
Campaign: under $100

The same security-task RL experiment, run two ways: rented 8×H200 nodes versus a serverless training API. The benchmark, the cost ledger, and the case for open weights.

Two months ago I built the only vLLM lane for Inkling-Small on two DGX Sparks and released the GLP-41 steering vectors. The point of the two-node recipe was a local, open-weight US model I could inspect and steer myself, not another API dependency. Yesterday Thinking Machines shipped Inkling 2 Small - 594B total parameters, 17B active, hybrid MoE - and per their stated approach the weights land under Apache 2.0 after external red-teaming completes, following the path they outlined for a safe transition to open weights. Between those two dates, my RL pipeline for security tasks went through a full generation cycle: five GPU-rental training campaigns on GLM-5.3-Flash that cost roughly $12,000 of metered GPU time, a sixth on DeepSeek-V4.1-Flash-1017 that burned about $4,600 and never trained a single step, and then - this week - a complete 60-step run on Inkling 2 Small that cost about $35.

RL on Matt Suiche

RLVR on Inkling 2 Small: Beating GLM-5.3-Flash in 60 Steps for $22