Instructions to use EchoLabs33/qwen2.5-coder-3b-hxq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EchoLabs33/qwen2.5-coder-3b-hxq with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EchoLabs33/qwen2.5-coder-3b-hxq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EchoLabs33/qwen2.5-coder-3b-hxq")
model = AutoModelForCausalLM.from_pretrained("EchoLabs33/qwen2.5-coder-3b-hxq", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use EchoLabs33/qwen2.5-coder-3b-hxq 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 EchoLabs33/qwen2.5-coder-3b-hxq
# Run inference directly in the terminal:
llama cli -hf EchoLabs33/qwen2.5-coder-3b-hxq

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EchoLabs33/qwen2.5-coder-3b-hxq
# Run inference directly in the terminal:
llama cli -hf EchoLabs33/qwen2.5-coder-3b-hxq

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 EchoLabs33/qwen2.5-coder-3b-hxq
# Run inference directly in the terminal:
./llama-cli -hf EchoLabs33/qwen2.5-coder-3b-hxq

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 EchoLabs33/qwen2.5-coder-3b-hxq
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EchoLabs33/qwen2.5-coder-3b-hxq

Use Docker

docker model run hf.co/EchoLabs33/qwen2.5-coder-3b-hxq

LM Studio
Jan

vLLM

How to use EchoLabs33/qwen2.5-coder-3b-hxq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EchoLabs33/qwen2.5-coder-3b-hxq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EchoLabs33/qwen2.5-coder-3b-hxq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EchoLabs33/qwen2.5-coder-3b-hxq

SGLang

How to use EchoLabs33/qwen2.5-coder-3b-hxq with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "EchoLabs33/qwen2.5-coder-3b-hxq" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EchoLabs33/qwen2.5-coder-3b-hxq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "EchoLabs33/qwen2.5-coder-3b-hxq" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EchoLabs33/qwen2.5-coder-3b-hxq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use EchoLabs33/qwen2.5-coder-3b-hxq with Ollama:
```
ollama run hf.co/EchoLabs33/qwen2.5-coder-3b-hxq
```

Unsloth Studio

How to use EchoLabs33/qwen2.5-coder-3b-hxq 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 EchoLabs33/qwen2.5-coder-3b-hxq 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 EchoLabs33/qwen2.5-coder-3b-hxq to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EchoLabs33/qwen2.5-coder-3b-hxq to start chatting

How to use EchoLabs33/qwen2.5-coder-3b-hxq with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EchoLabs33/qwen2.5-coder-3b-hxq

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": "EchoLabs33/qwen2.5-coder-3b-hxq"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use EchoLabs33/qwen2.5-coder-3b-hxq with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EchoLabs33/qwen2.5-coder-3b-hxq

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "EchoLabs33/qwen2.5-coder-3b-hxq" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use EchoLabs33/qwen2.5-coder-3b-hxq with Docker Model Runner:
```
docker model run hf.co/EchoLabs33/qwen2.5-coder-3b-hxq
```

Lemonade

How to use EchoLabs33/qwen2.5-coder-3b-hxq with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EchoLabs33/qwen2.5-coder-3b-hxq

Run and chat with the model

lemonade run user.qwen2.5-coder-3b-hxq-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use EchoLabs33/qwen2.5-coder-3b-hxq with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EchoLabs33/qwen2.5-coder-3b-hxq

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 EchoLabs33/qwen2.5-coder-3b-hxq

Run Hermes

hermes

Atomic Chat

Qwen2.5-Coder-3B-HXQ

Qwen2.5-Coder-3B-Instruct compressed with HXQ (HelixCode vector quantization).

Available as both HuggingFace safetensors (via helix-substrate) and native GGUF (via llama.cpp HXQ fork).

GGUF Runtime Benchmark (RTX 3090)

Benchmarked against standard GGUF K-quants on RTX 3090, full GPU offload (-ngl 99), using the hxq-affine-type branch at commit 580e9a2.

Decode Speed (tg128, 3 runs)

Format	Size	bpw	tok/s	vs Q4	vs Q6
Q4_K_M	1.95 GB	4.5	245.03	100%	120%
Q5_K_M	2.07 GB	5.5	229.00	93.5%	112%
HXQ_AF6	2.26 GB	6.25	226.53	92.4%	110.6%
Q6_K	2.36 GB	6.56	204.86	83.6%	100%

Perplexity (WikiText-2, 50 chunks, ctx=512)

Format	bpw	PPL	vs Q4
HXQ_AF6	6.25	9.954	-0.118 (best)
Q6_K	6.56	9.964	-0.108
Q5_K_M	5.5	10.004	-0.068
Q4_K_M	4.5	10.072	baseline

HumanEval (evalplus v0.3.1, greedy, pass@1)

Format	HumanEval base	HumanEval+
HXQ_AF6	84.1%	78.0%
Q5_K_M	83.5%	75.6%
Q6_K	83.5%	78.0%
Q4_K_M	82.3%	78.0%

Prefill (pp512, 3 runs)

Format	tok/s	vs Q4
Q4_K_M	8974	100%
Q5_K_M	8543	95.2%
Q6_K	8173	91.1%
HXQ_AF6	7430	82.8%

Summary: HXQ_AF6 has the lowest perplexity, the highest HumanEval base pass@1, and decodes 10.6% faster than Q6_K while being smaller (2.26 vs 2.36 GB). It trades ~7.6% decode speed vs Q4_K_M for better quality preservation at 6.25 bpw.

Reproducibility

All claims are within-run comparisons using the same dataset, llama.cpp commit, and hardware. Do not compare these PPL numbers with numbers from other runs using different model variants, dataset files, or build configurations.

Full receipt with SHA256 artifact hashes, exact commands, and raw HumanEval outputs: bench_receipt.json

Install and Run

Option 1: Native GGUF (llama.cpp)

# Build llama.cpp with HXQ support
git clone -b hxq-affine-type https://github.com/echo313unfolding/llama.cpp.git
cd llama.cpp && mkdir build && cd build
cmake .. -DGGML_CUDA=ON && make -j$(nproc) llama-cli

# Run
./bin/llama-cli -m qwen2.5-coder-3b-instruct-hxq-affine6.gguf \
  -ngl 99 -p "def fibonacci(n):" -n 128

Option 2: HuggingFace (Python)

pip install "helix-substrate[hf]"

import helix_substrate  # registers the HXQ quantizer with HuggingFace
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("EchoLabs33/qwen2.5-coder-3b-hxq")
tokenizer = AutoTokenizer.from_pretrained("EchoLabs33/qwen2.5-coder-3b-hxq")

inputs = tokenizer("def fibonacci(n):", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Safetensors Benchmark

	Dense (BF16)	HXQ (safetensors)
Size	6.2 GB	3.84 GB
Perplexity (WikiText-2, 2048 ctx)	6.113	6.230 (+1.92%)
Compression ratio	1x	1.6x
Compressed modules	0	252 HelixLinear layers

Note: The safetensors PPL (6.230) and GGUF PPL (9.954) use different evaluation configurations (ctx=2048/stride=512 vs ctx=512/50 chunks). They are not directly comparable.

Good to Know

GPU and CPU supported — runs on any CUDA GPU or CPU via standard PyTorch. Native GGUF runs via llama.cpp.
Fine-tunable via LoRA — compressed weights remain frozen, but LoRA adapters attach to each HelixLinear layer via HelixLinearSTE. See helix-substrate for training infrastructure.
Requires helix-substrate for safetensors path — the quantizer is not built into transformers. You need pip install "helix-substrate[hf]".
Requires llama.cpp HXQ fork for GGUF path — standard llama.cpp does not have HXQ type support yet.
Tied embeddings — lm_head shares embed_tokens, stored at full precision.

What is HXQ?

HXQ is a weight compression codec based on vector quantization with per-group affine correction:

Each weight matrix is replaced by a 256-entry codebook + uint8 index matrix + per-group affine scale/offset
The compressed form is the executable — codebook[indices] * scale + offset during matmul, no decompression step
Works on any nn.Linear regardless of architecture (Transformer, Mamba, MLP)
No calibration data required — codebooks are fit from the weights alone via k-means
6.25 bits per weight in the GGUF affine-6 format

Companion Models

Same codec, multiple architectures:

Model	Architecture	GGUF	Safetensors
qwen2.5-7b-instruct-hxq	Transformer	Yes	Yes
qwen2.5-3b-instruct-hxq	Transformer	Yes	Yes
qwen2.5-coder-1.5b-hxq	Transformer (code)	Yes	Yes
qwen2.5-14b-instruct-hxq	Transformer	Yes	Yes
qwen2.5-sentinel-3b-hxq	Transformer (security)	—	Yes

Citation

@software{hxq_2026,
  title={HXQ: Vector Quantization with Per-Group Affine Correction for Neural Network Weight Compression},
  author={Echo Labs},
  year={2026},
  url={https://github.com/echo313unfolding/helix-substrate}
}