Qwythos-9B-Claude-Mythos-5-1M-GGUF

Instructions to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF",
	filename="Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alexukraine/Qwythos-9B-Claude-Mythos-5-1M-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 alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf alexukraine/Qwythos-9B-Claude-Mythos-5-1M-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 alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Ollama
How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Ollama:
```
ollama run hf.co/alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
```

Unsloth Studio

How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-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 alexukraine/Qwythos-9B-Claude-Mythos-5-1M-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 alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF to start chatting

How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

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": "alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

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 alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Docker Model Runner:
```
docker model run hf.co/alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
```

Lemonade

How to use alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alexukraine/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwythos-9B-Claude-Mythos-5-1M-GGUF-Q4_K_M

List all available models

lemonade list

Qwythos-9B-Claude-Mythos-5-1M-GGUF / TEST_REPORT.md

alexukraine

Duplicate from empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

6ee9cef 2 days ago

preview code

Raw

History Blame Contribute Delete

3.72 kB

Qwythos GGUF v2 release verification

Release verification was performed on 2026-06-22 with llama.cpp d0f9d2e5ac5d4f51763755958b8f353fed01aaa2 and an NVIDIA RTX 5090.

Artifact manifest

Artifact	Bytes	SHA-256
`Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf`	17,920,697,344	`c49e2e419c0fc9f7cca0a7e0699fa3075fa1ec2913bda6f6841194b19cf4ce29`
`Qwythos-9B-Claude-Mythos-5-1M-Q4_K_M.gguf`	5,629,109,248	`0de41ff56ab4eff26764437b276f0bd5d20f44232add34e14c4f593fa1aeb08f`
`Qwythos-9B-Claude-Mythos-5-1M-Q5_K_M.gguf`	6,467,970,048	`51dee6e6ddaeb08a06bee258ac5c58f4186f55d156d6403c2db67cf2f3226280`
`Qwythos-9B-Claude-Mythos-5-1M-Q6_K.gguf`	7,359,259,648	`05f2420a669a83ae239d1328c6e83d9fc19e8a4b8dab5d0673cab28cc161dfc5`
`Qwythos-9B-Claude-Mythos-5-1M-Q8_0.gguf`	9,527,501,824	`ecf51ef3904694e04a1967a06fe7539619c34e6e81a721fc5f5415827081d8f6`
`Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf`	18,407,321,536	`c704996e63c3e31a1e7040278b1204aabf8a6dad0b07f3c8da7b429d2ed30b31`
`Qwythos-9B-Claude-Mythos-5-1M-MTP-Q4_K_M.gguf`	5,887,668,160	`24ee22e0f5d9f0d3d615809607f365c728d9b0c3f3fb6eb19d8bd83a1c2933d8`
`Qwythos-9B-Claude-Mythos-5-1M-MTP-Q5_K_M.gguf`	6,726,528,960	`c4e3c47b17a93cc1566abcee4a0c9a4413b172a6f8be7f2a8824495907e9e893`
`Qwythos-9B-Claude-Mythos-5-1M-MTP-Q6_K.gguf`	7,617,818,560	`eae2adb4b451f673218fba96ebdc024fb95c4026ef35a56837dc9af47f99ca39`
`Qwythos-9B-Claude-Mythos-5-1M-MTP-Q8_0.gguf`	9,786,060,736	`34eada291b4f4d1b8592f53d1739c7a2e029011b5bc2624b979b0a544562a5e9`
`mmproj-Qwythos-9B-Claude-Mythos-5-1M-F16.gguf`	918,165,472	`f977efc337a2ac2ba183eea0c73e25b75fc240d56c05ed4d9b56ab451f64c82c`

shasum -a 256 -c SHA256SUMS passed for all 11 GGUF artifacts after conversion and testing.

Structural checks

All ten text GGUFs passed these shared assertions:

GGUF v3 and qwen35 architecture;
1,048,576-token declared context;
Qwen3.6-derived chat template markers present;
fixed Qwythos/Empero AI identity instruction present.

The five normal v2 replacement files additionally verified as 32-block trunk-only GGUFs with no nextn_predict_layers key and no MTP tensors.

The five -MTP- v2 variants additionally verified as 33-block GGUFs with qwen35.nextn_predict_layers = 1, all 15 restored MTP tensors present, and MTP matrices retained at Q8_0 in every quantized variant.

The MTP tensors come from pinned Qwen3.5-9B base commit c202236235762e1c871ad0ccb60c8ee5ba337b9a. The source fine-tune declares one MTP layer but does not publish its MTP tensors. Only the draft head is restored; the Qwythos trunk and output layers remain unchanged.

Live tests

Variant / mode	Identity	Generation	Tools	Other
BF16 MTP	Pass	Pass	—	—
Q4_K_M MTP	Pass	Pass	Pass	Tool result round trip passed
Q5_K_M MTP	Pass	Pass	—	—
Q6_K MTP	Pass	Pass	—	—
Q8_0 MTP	Pass	Pass	Pass	Tool result round trip passed; no malformed output
Q4_K_M MTP + draft speculation	Pass	Pass	Pass	76/150 draft tokens accepted (50.7%)
Q4_K_M MTP + 1M context	Pass	Pass	—	Server loaded `n_ctx = 1048576`
Q4_K_M MTP + F16 mmproj	Pass	Pass	—	Correctly identified a generated red-square image

The normal v2 replacement files were rebuilt from the same fixed tokenizer/template source with --no-mtp and structurally verified after quantization. The 1M-context check verifies full context allocation and successful generation at that setting; it is not a million-token retrieval benchmark.

Machine-readable responses are in reports/; relevant llama.cpp logs are in logs/.