Instructions to use john-broadway/SmolLM2-360M-RYS-12-15-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use john-broadway/SmolLM2-360M-RYS-12-15-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="john-broadway/SmolLM2-360M-RYS-12-15-GGUF",
	filename="SmolLM2-360M-RYS-12-15-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use john-broadway/SmolLM2-360M-RYS-12-15-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M

Use Docker

docker model run hf.co/john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use john-broadway/SmolLM2-360M-RYS-12-15-GGUF with Ollama:
```
ollama run hf.co/john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M
```

Unsloth Studio new

How to use john-broadway/SmolLM2-360M-RYS-12-15-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for john-broadway/SmolLM2-360M-RYS-12-15-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for john-broadway/SmolLM2-360M-RYS-12-15-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for john-broadway/SmolLM2-360M-RYS-12-15-GGUF to start chatting

Docker Model Runner
How to use john-broadway/SmolLM2-360M-RYS-12-15-GGUF with Docker Model Runner:
```
docker model run hf.co/john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M
```

Lemonade

How to use john-broadway/SmolLM2-360M-RYS-12-15-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull john-broadway/SmolLM2-360M-RYS-12-15-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM2-360M-RYS-12-15-GGUF-Q4_K_M

List all available models

lemonade list

SmolLM2-360M-RYS-12-15

SmolLM2-360M-Instruct with layers 12-14 duplicated. A mid-stack reasoning + math circuit runs twice on every forward pass.

32 base layers → 35 after duplication. No training, no merging, no weight changes.

Reasoning 29.41% → 52.94% (+23.53). Math 0.279 → 0.3688 (+8.98). EQ 77.66 → 72.74 (−4.92).

Results

Metric	Baseline	RYS (12,15)	Delta
Math	0.279	0.3688	+8.98
EQ	77.66	72.74	−4.92
Reasoning	29.41%	52.94%	+23.53

The middle SmolLM2 sibling. Swept with the full block-size search [3,4,5] across 66 configurations — the same search depth as the rest of the v2 corpus, broader than the SmolLM2-1.7B sibling's narrower [3,4] search. Responds normally with +23.53 reasoning and a +8.98 math gain, reinforcing the 135M's signal: the 1.7B negative result is the anomaly, not the family. The narrower 1.7B sweep remains a methodological caveat worth a re-sweep with full blocks to resolve definitively.

Pick this when you want a tiny model with strong reasoning + math lift and can absorb the small EQ trade-off.

Usage

llama-server -m SmolLM2-360M-RYS-12-15-Q4_K_M.gguf -ngl 99

Full sweep data

66 configurations tested. (12,15) block-3 is the best-combined pick. Full per-config sweep + cross-architecture analysis: v2 dataset.

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):

SmolLM2-135M-RYS-18-22-GGUF — baseline reasoning 17.65%, peak Δ +17.65% (responds)
360M (this card) — baseline reasoning 29.41%, peak Δ +23.53% (responds; full block search [3,4,5])
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 on Qwen2-72B; sweep + probe toolkit by alainnothere.