Instructions to use john-broadway/Yi-1.5-6B-RYS-20-23-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use john-broadway/Yi-1.5-6B-RYS-20-23-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="john-broadway/Yi-1.5-6B-RYS-20-23-GGUF",
	filename="Yi-1.5-6B-RYS-20-23-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 Settings

llama.cpp

How to use john-broadway/Yi-1.5-6B-RYS-20-23-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/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/Yi-1.5-6B-RYS-20-23-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/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf john-broadway/Yi-1.5-6B-RYS-20-23-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/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf john-broadway/Yi-1.5-6B-RYS-20-23-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/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf john-broadway/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M

Use Docker

docker model run hf.co/john-broadway/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use john-broadway/Yi-1.5-6B-RYS-20-23-GGUF with Ollama:
```
ollama run hf.co/john-broadway/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M
```

Unsloth Studio

How to use john-broadway/Yi-1.5-6B-RYS-20-23-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/Yi-1.5-6B-RYS-20-23-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/Yi-1.5-6B-RYS-20-23-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/Yi-1.5-6B-RYS-20-23-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use john-broadway/Yi-1.5-6B-RYS-20-23-GGUF with Docker Model Runner:
```
docker model run hf.co/john-broadway/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M
```

Lemonade

How to use john-broadway/Yi-1.5-6B-RYS-20-23-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull john-broadway/Yi-1.5-6B-RYS-20-23-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Yi-1.5-6B-RYS-20-23-GGUF-Q4_K_M

List all available models

lemonade list

Yi-1.5-6B-RYS-20-23

Yi-1.5-6B-Chat with layers 20-22 duplicated. A late-stack triple-coupled circuit — boosting math, EQ, and reasoning simultaneously — runs twice on every forward pass.

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

Reasoning 76.47% → 88.23% (+11.76). EQ 86.09 → 91.87 (+5.78). Math 0.518 → 0.5537 (+3.57). Combined Δ +21.11 — rare three-way positive lift in the v2 corpus.

Results

Metric	Baseline	RYS (20,23)	Delta
Math	0.518	0.5537	+3.57
EQ	86.09	91.87	+5.78
Reasoning	76.47%	88.23%	+11.76

The three-way lift. Most RYS sweeps surface a trade-off — math vs EQ, reasoning vs EQ, math vs reasoning. Yi-1.5-6B is the only model in the v2 corpus where the single best configuration delivers simultaneous positive lift across all three probes. The combined Δ +21.11 is reached without sacrificing any dimension.

Yi-1.5-6B was the closing sweep of the v2 cross-architecture queue (2026-05-12), bringing the corpus to N=21 and locking the final correlation at r = −0.726. The narrow boost signal (1 of 66 configs reasoning-boosters) means the triple-coupled config is specific to (20,23) block-3.

Pick this when you want simultaneous lift across all three dimensions without trade-off.

Usage

llama-server -m Yi-1.5-6B-RYS-20-23-Q4_K_M.gguf -ngl 99

Full sweep data

66 configurations tested. (20,23) block-3 is the unique three-way-positive 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. Yi-1.5-6B is on-curve at high baseline; the three-way coupling is what makes its row distinctive. 13 deployable RYS-applied weight repos covering every non-zero-lift variant.

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.

Downloads last month: 154

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for john-broadway/Yi-1.5-6B-RYS-20-23-GGUF

Base model

01-ai/Yi-1.5-6B-Chat

Quantized

(30)

this model

Collection including john-broadway/Yi-1.5-6B-RYS-20-23-GGUF

RYS Sovereign Collection v2

Collection

Qwen3-family cohort (0.6B/1.7B/8B) + cross-architecture sweep corpus (21 variants, 10 families). v1 collection: Qwen2.5 cross-scale + Qwen3-32B. • 18 items • Updated 29 days ago