Instructions to use thinktecture/gemma3-4b-ft-nextera-q4_k_m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thinktecture/gemma3-4b-ft-nextera-q4_k_m with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="thinktecture/gemma3-4b-ft-nextera-q4_k_m",
	filename="gemma3-4b-ft-nextera-q4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use thinktecture/gemma3-4b-ft-nextera-q4_k_m with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf thinktecture/gemma3-4b-ft-nextera-q4_k_m: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 thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf thinktecture/gemma3-4b-ft-nextera-q4_k_m: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 thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M

Use Docker

docker model run hf.co/thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M

LM Studio
Jan

vLLM

How to use thinktecture/gemma3-4b-ft-nextera-q4_k_m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thinktecture/gemma3-4b-ft-nextera-q4_k_m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thinktecture/gemma3-4b-ft-nextera-q4_k_m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M

Ollama
How to use thinktecture/gemma3-4b-ft-nextera-q4_k_m with Ollama:
```
ollama run hf.co/thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M
```

Unsloth Studio new

How to use thinktecture/gemma3-4b-ft-nextera-q4_k_m 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 thinktecture/gemma3-4b-ft-nextera-q4_k_m 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 thinktecture/gemma3-4b-ft-nextera-q4_k_m to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for thinktecture/gemma3-4b-ft-nextera-q4_k_m to start chatting

Docker Model Runner
How to use thinktecture/gemma3-4b-ft-nextera-q4_k_m with Docker Model Runner:
```
docker model run hf.co/thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M
```

Lemonade

How to use thinktecture/gemma3-4b-ft-nextera-q4_k_m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull thinktecture/gemma3-4b-ft-nextera-q4_k_m:Q4_K_M

Run and chat with the model

lemonade run user.gemma3-4b-ft-nextera-q4_k_m-Q4_K_M

List all available models

lemonade list

⚠️ Conference talk demo — not production weights.

This model accompanies a conference keynote on local on-device AI. Published as a reference for the fine-tuning patterns shown on stage — not a deployable artefact. No security audit, no SLA, pinned to the talk's state.

Source repository: thinktecture-labs/local-multi-model-agent-slm
Threat model + out-of-scope: SECURITY.md
Licensing details: MODEL_LICENSES.md
All five models in the stack: Collection — Local Multi-Model Agent — nextera fine-tunes

Gemma3-4B FT (Q4_K_M) — RAG Synthesis (+ Vision) — production


Base model	`google/gemma-3-4b-it` (4.3B params, multimodal: text + vision via mmproj)
License	Gemma Terms of Use
Provenance	`llama-quantize` from the F16 sibling GGUF (no separate training run — quantization only). See `finetune/convert_gemma3_4b_to_gguf.sh`.
File size	2.49 GB (vs 7.77 GB for F16) — ~3× memory-bandwidth headroom on decode
Hardware tested	RTX PRO 6000 (Blackwell sm_120), MBP M5 Max (Metal), DGX Spark (GB10 sm_121), Strix Halo (Vulkan/RDNA 3.5) — byte-deterministic across all four
Intended use	Production RAG response synthesis. Points-of-use: `scenarios/<scenario>.json:synthesis_4b_gguf_ft`. The vision channel uses the same GGUF (multimodal via the same mmproj as the F16 variant).
Out of scope	Tool calling (delegated to Qwen3.5-4B FT). Free-form chat without retrieved context.
Reference eval (Nextera, 2026-05-17)	Identical-quality to F16 on the 80-query RAG groundtruth set (MBP same-machine F16-vs-Q4_K_M A/B: 55/80 vs 54/80 = 1-query phrasing noise, zero semantic regression). Realized perf gains vs F16: RAG p50 -25% to -57%, image-query p50 -32% to -61% across the four-backend fleet.
Known failure modes	Same as F16 sibling. Q4_K_M-specific quantization artifacts not observed in our evals; would expect them most on rare-token tail behavior.

Downloads last month: 37

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

Model tree for thinktecture/gemma3-4b-ft-nextera-q4_k_m

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(221)

this model