Instructions to use Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF",
	filename="Qwen3.5-27B-GCTH_ST_V112-IQ3_XS-16gb_vram_optimized.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 Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS
# Run inference directly in the terminal:
llama-cli -hf Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS
# Run inference directly in the terminal:
llama-cli -hf Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

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 Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS
# Run inference directly in the terminal:
./llama-cli -hf Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

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 Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

Use Docker

docker model run hf.co/Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

LM Studio
Jan
Ollama
How to use Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF with Ollama:
```
ollama run hf.co/Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS
```

Unsloth Studio

How to use Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-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 Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-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 Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF to start chatting

How to use Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF with Docker Model Runner:
```
docker model run hf.co/Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS
```

Lemonade

How to use Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gammaception/Qwen3.5-27B-Thireus-16gb-optimized-GGUF:IQ3_XS

Run and chat with the model

lemonade run user.Qwen3.5-27B-Thireus-16gb-optimized-GGUF-IQ3_XS

List all available models

lemonade list

Gammaception commited on Apr 3

Commit

e733a92

verified ·

1 Parent(s): 5c61dcf

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -9

README.md CHANGED Viewed

@@ -11,14 +11,15 @@ Best 16 gb config for GC IQ3_M: (headless 80k ctx kv-cache@(q8_0,q8_0), -ub 256,
 EDIT 24/03/26: Updated GGUF to fix coding quality, new charts
-| | unsloth ud-iq3_xxs | bartowski iq3_xs | mungert iq3_xs | GC-Thireus iq3_m | bartowski iq3_m | unsloth ud-q3_k_xl | bartowski iq4_xs |
-| --- | --- | --- | --- | --- | --- | --- | --- |
-| Size (GiB) | 10.716 | 11.357 | 12.078  | 12.091 | 12.240 | 13.447 | 14.130 |
-| PPL mean | 7.349445 | 7.275691 | 7.146062 | 6.966245 | 7.166074 | 7.095870 | 6.932149 |
-| KLD mean | 0.080486 | 0.066744 | 0.053966 | 0.040473 | 0.057891 | 0.034783 | 0.019950 |
-| Same top p | 88.546 | 89.837 | 90.625 | 92.075 | 90.782 | 92.656 | 94.610 |
 kl logits from unsloth ud-q6_k_xl (best i can fit), wikitext-2 512ctx bf16 kv
-![ppl_graph](charts4/pplMean.png "Chart showing PPL analysis of quants")
-![kld_graph](charts4/kldMean.png "Chart showing KLD analysis of quants")
-![tpp_graph](charts4/sameTopP.png "Chart showing Top P analysis of quants")

 EDIT 24/03/26: Updated GGUF to fix coding quality, new charts
+EDIT 03/04/26: New variants with better quality ratios, update charts
+| | unsloth ud-iq3_xxs | bartowski iq3_xs | GC-Thireus iq3_xs | mungert iq3_xs | bartowski iq3_m | GC-Thireus iq3_m | unsloth ud-q3_k_xl | bartowski iq4_xs |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| Size (GiB) | 10.716 | 11.357 | 11.800 | 12.078 | 12.240 | 12.465 | 13.447 | 14.130 |
+| PPL mean | 7.349445 | 7.275691 | 7.003592 | 7.146062 | 7.166074 | 6.886104 | 7.095870 | 6.932149 |
+| KLD mean | 0.080486 | 0.066744 | 0.044320 | 0.053966 | 0.057891 | 0.032533 | 0.034783 | 0.019950 |
+| Same top p | 88.546 | 89.837 | 91.560 | 90.625 | 90.782 | 92.926 | 92.656 | 94.610 |
 kl logits from unsloth ud-q6_k_xl (best i can fit), wikitext-2 512ctx bf16 kv
+![ppl_graph](charts5/pplMean.png "Chart showing PPL analysis of quants")
+![kld_graph](charts5/kldMean.png "Chart showing KLD analysis of quants")
+![tpp_graph](charts5/sameTopP.png "Chart showing Top P analysis of quants")