---
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M-Instruct
tags:
  - rys
  - layer-duplication
  - reasoning-circuits
  - gguf
  - sovereign-collection-v2
---

# SmolLM2-135M-RYS-18-22

SmolLM2-135M-Instruct with layers 18-21 duplicated. The late-stack reasoning + EQ circuit runs twice on every forward pass.

30 base layers → 34 after duplication. No training, no merging, no weight changes.

**Reasoning 17.65% → 35.30% (+17.65). EQ 44.53 → 57.58 (+13.05). Math 0.315 → 0.303 (−1.20).**

## Results

| Metric | Baseline | RYS (18,22) | Delta |
|--------|----------|-------------|-------|
| Math | 0.315 | 0.303 | −1.20 |
| EQ | 44.53 | 57.58 | +13.05 |
| Reasoning | 17.65% | 35.30% | +17.65 |

**The tiniest responder.** SmolLM2-135M is the smallest model in the v2 corpus by an order of magnitude. RYS lifts both reasoning (+17.65 absolute) AND EQ (+13.05) simultaneously — the response is unremarkable on its own, but the comparison to sibling SmolLM2-1.7B (which lifts **zero percent on reasoning**) makes this card load-bearing: it falsifies the "SmolLM2 training recipe doesn't work with RYS" hypothesis. **The 1.7B negative result is uniquely anomalous within the family, not architectural.**

Pick this when you want the smallest possible model with reasoning + EQ lift. At 110MB Q4_K_M, this is the lightest RYS-applied checkpoint in the collection.

## Usage

```
llama-server -m SmolLM2-135M-RYS-18-22-Q4_K_M.gguf -ngl 99
```

## Full sweep data

40 configurations tested. (18,22) block-4 is the best-combined pick. Full per-config sweep + cross-architecture analysis: [v2 dataset](https://huggingface.co/datasets/john-broadway/rys-sovereign-collection-v2).


Part of the RYS Sovereign Collection v2.

---

## Where this sits in the Sovereign Collection

**v1 — Qwen2.5 cross-scale + Qwen3-32B headline crossover.** 5 model repos.

**v2 — cross-architecture corpus.** 21 model variants across 10 architecture families. Inverse correlation (r = −0.726): weak baselines lift more, in their weakest dimension. 13 deployable RYS-applied weight repos covering every non-zero-lift variant.

**SmolLM2 family picture** (all Q4_K_M):

- 135M (this card) — baseline reasoning 17.65%, peak Δ **+17.65%** (responds)
- [`SmolLM2-360M-RYS-12-15-GGUF`](https://huggingface.co/john-broadway/SmolLM2-360M-RYS-12-15-GGUF) — baseline reasoning 29.41%, peak Δ **+23.53%** (responds)
- [`SmolLM2-1.7B-RYS-eval`](https://huggingface.co/john-broadway/SmolLM2-1.7B-RYS-eval) — baseline reasoning 58.82%, peak Δ **+0.00%** (does NOT respond; eval-only — no RYS-applied weights since no lift to deliver)

**Credit**

John Broadway, with collaboration from Claude (Opus 4.6 in April 2026 sweep generation and build pipeline; Opus 4.7 in May 2026 cross-architecture analysis and publication). Original RYS method by [David Ng](https://dnhkng.github.io/posts/rys/) on Qwen2-72B; sweep + probe toolkit by [alainnothere](https://github.com/alainnothere/llm-circuit-finder).