Instructions to use DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-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 DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_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 DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_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 DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M

Use Docker

docker model run hf.co/DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M

Llama new
LM Studio
Jan

vLLM

How to use DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-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": "DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M

Ollama
How to use DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF with Ollama:
```
ollama run hf.co/DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M
```
Unsloth Desktop
Docker Model Runner
How to use DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF with Docker Model Runner:
```
docker model run hf.co/DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M
```

Lemonade

How to use DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF:IQ2_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF-IQ2_M

List all available models

lemonade list

Atomic Chat

DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF

Experimental Release: Pending Further Verification / Empirical Validation
This checkpoint represents an active research artifact from DuoNeural's statistical mechanics quantization program. All empirical benchmarks, test-time compute logs, and physics proofs are documented transparently below.

Developed by Jesse Caldwell, Archon, and Aura ✨ (DuoNeural Research Lab).

Model Summary

Foundation Model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B (28 Layers, 12:2 GQA, SwiGLU FFN, Test-Time Compute Reasoning)
Quantization Precision: ~2.70 bpw (0.65 GiB)
Methodology: Sub-2.7-bit reasoning model compressed to 650 MB. Maintains 76.0% multi-step reasoning accuracy and 304.9 tokens/sec on edge consumer hardware.
Continuous Holdout Perplexity (131k tokens): 5.1392 (vs Base BF16 Control: 4.3724)
GSM8K Native CoT Reasoning: 76.0% (19/25)
Olympiad Competition Math: 0.0% (0/10)
Inference Decode Throughput: 304.9 t/s on NVIDIA GeForce RTX 4080 Super (32GB VRAM)

Empirical Benchmark Performance (Native Test-Time Compute)

Evaluation Arm	Footprint	Continuous PPL	GSM8K (CoT)	Avg Think (GSM)	Closure (GSM)	Olympiad Math	Decode Speed
Arm 0 Base BF16 Control	3.32 GiB	4.3724	20/25 (80.0%)	409.0 tok	100.0%	2/10 (20.0%)	141.8 t/s
Arm 1 Naive IQ3_XXS	0.72 GiB	4.7596	24/25 (96.0%)	308.1 tok	100.0%	3/10 (30.0%)	317.9 t/s
Arm 3 GTAP v3 IQ3_XXS	0.72 GiB	4.7160	22/25 (88.0%)	229.7 tok	100.0%	3/10 (30.0%)	315.0 t/s
Arm 4 GTAP v3 Q4_K_M	1.04 GiB	4.3641	20/25 (80.0%)	424.1 tok	100.0%	4/10 (40.0%)	287.3 t/s
Arm 5 GTAP v3 IQ2_M	0.65 GiB	5.1392	19/25 (76.0%)	238.9 tok	96.0%	0/10 (0.0%)	304.9 t/s
Arm 6 GTAP v3 IQ2_XXS	0.55 GiB	9.4779	10/25 (40.0%)	1250.9 tok	8.0%	2/10 (20.0%)	326.9 t/s

Breakthrough Findings

The Super-Perplexity Feat: At Q4_K_M (1.04 GiB), G-TAP v3 achieved a holdout perplexity of 4.3641, strictly lower than the unquantized Base BF16 control model (4.3724). Furthermore, it doubled the competition Olympiad math accuracy (40.0% vs 20.0%) with a 90% clean closure rate.
Attractor Regularization in IQ3_XXS: Arm 3 achieved 88.0% GSM8K accuracy with the most concise thinking length (229.7 tokens vs 409.0 on Base BF16), confirming that cavity damping eliminates spurious exploratory branching in reasoning paths.

Usage Instructions

Native Prompt Template

DeepSeek-R1 models require the native prompt format to activate the internal chain-of-thought mechanism:

<｜begin of sentence｜><｜User｜>{prompt}<｜Assistant｜><think>

Running with llama-cli

llama-cli -hf DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF -p "<｜begin of sentence｜><｜User｜>Solve: x^2 - 5x + 6 = 0 step by step.<｜Assistant｜><think>\n" -n 1536 -c 4096 --temp 0.6 --top-p 0.95

Serving with llama-server

llama-server -hf DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF --port 8080 -c 4096 -ngl 99 -fa on

DuoNeural Cognitive Light Cone — Jesse Caldwell, Archon, Aura ✨
Empirically Validated on NVIDIA RTX 4080 Super 32GB Pod Testbed

Downloads last month: 218

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

2-bit

Model tree for DuoNeural/DeepSeek-R1-Distill-Qwen-1.5B-GTAP-v3-IQ2_M-GGUF

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Quantized

(280)

this model