Instructions to use tg-techie-agents/Q1D-4B-Blk0-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tg-techie-agents/Q1D-4B-Blk0-V2 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 tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0
# Run inference directly in the terminal:
llama cli -hf tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0
# Run inference directly in the terminal:
llama cli -hf tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0

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 tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0
# Run inference directly in the terminal:
./llama-cli -hf tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0

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 tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0

Use Docker

docker model run hf.co/tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0

LM Studio
Jan

vLLM

How to use tg-techie-agents/Q1D-4B-Blk0-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tg-techie-agents/Q1D-4B-Blk0-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tg-techie-agents/Q1D-4B-Blk0-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0

Ollama
How to use tg-techie-agents/Q1D-4B-Blk0-V2 with Ollama:
```
ollama run hf.co/tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0
```
Unsloth Desktop
Docker Model Runner
How to use tg-techie-agents/Q1D-4B-Blk0-V2 with Docker Model Runner:
```
docker model run hf.co/tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0
```

Lemonade

How to use tg-techie-agents/Q1D-4B-Blk0-V2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tg-techie-agents/Q1D-4B-Blk0-V2:Q1_0

Run and chat with the model

lemonade run user.Q1D-4B-Blk0-V2-Q1_0

List all available models

lemonade list

Atomic Chat

Q1D 4B Blk0 V2

Research artifact from Q1 Descent — reconstructing per-block 1-bit "intelligence-density" recovery for open-weight Qwen3 models. Shelved 2026-06-19; published for the record. See the project debrief for context.

Method (Q1_0_g128, 1.125 bpw). Selected transformer block(s) quantized to 1-bit (sign + per-128-group FP16 scale) and trained back toward the full-precision teacher with a straight-through estimator (FP32 master, forward = exact Q1_0 so signs and scales move; KL to the FP16 teacher on C4). All other blocks stay F16. This is not a fully 1-bit model — it isolates how far a small number of 1-bit blocks can be healed.

This model. Block 0 only at 1-bit (V2, 1200-step retrain); blocks 1-35 F16.

State / eval. GSM8K flex 0.84 / strict 0.81 (n=100; F16 teacher 0.76/0.56). Capability retained at 1 block. ~7/100 malformed on long generations.

Use. llama.cpp / LM Studio. Ships the closed-think (no-think) chat template; greedy (temp 0) recommended.

Caveats. Early research artifact, single seed, small-n evals (n=100, SE≈0.04 — don't over-read sub-0.08 gaps). Known occasional malformed-token outputs in some contexts (a byte-level-tokenizer effect; see debrief). Not affiliated with PrismML or the Qwen team.

Downloads last month: 5

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

1-bit

Model tree for tg-techie-agents/Q1D-4B-Blk0-V2

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(311)

this model