Instructions to use LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8")
model = AutoModelForMultimodalLM.from_pretrained("LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8

SGLang

How to use LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8 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 "LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8" \
    --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": "LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8",
		"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 "LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8" \
        --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": "LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8 with Docker Model Runner:
```
docker model run hf.co/LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8
```

Gemma-4-31B-Humanlike-Chat (FP8)

A 31B Gemma that texts like a person and still does the work, in FP8. No system prompt needed.

Results, examples and how it was made are on the main card: Gemma-4-31B-Humanlike-Chat-GGUF.

"Base" here always means Google's google/gemma-4-31B-it, the official release. It is not abliterated.

vLLM

Tested with vLLM 0.31.0 on an RTX PRO 6000 Blackwell (96 GB):

vllm serve LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8 --served-model-name humanlike-gemma \
  --max-model-len 16384 --language-model-only \
  --enable-auto-tool-choice --tool-call-parser gemma4 --reasoning-parser gemma4

Thinking is off by default, as in Google's Gemma 4 template. Send chat_template_kwargs: {"enable_thinking": true} per request to turn it on; the thinking comes back in its own field. It was trained with effort levels: add the line Reasoning effort: low or Reasoning effort: high to your system prompt, or no line for medium. Sampling: temperature 1.0, top_p 0.95, top_k 64 (Google's defaults in generation_config.json). For SGLang, point --model-path at this repo.

Format

FP8 weights (per channel) with dynamic per-token FP8 activations (FP8_DYNAMIC), made with llm-compressor 0.14.0.1 in compressed-tensors format. All 410 language linear layers are FP8; the vision tower, embeddings and lm_head stay BF16. Made from the BF16 weights.

VRAM

The weights take 30.4 GiB in vLLM. On the 96 GB test card at --gpu-memory-utilization 0.88, that left 50.0 GiB for the cache, 59,496 tokens. With less memory, take the GPTQ-Int4 repo or a GGUF from the main card.

Checks

Same check as every file on the main card: 5 fresh test chats against the reference (the merged BF16 weights in vLLM, which match Google's base plus the Humanlike adapter at runtime: KL 0.0005), served on vLLM 0.31.0, one NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB).

File	KL vs reference	Top-1 agreement	Greedy turns identical	Check fails (greedy / sampled)	Decode tok/s
BF16	reference	reference	reference	0 / 0	23
FP8	0.0034	100%	7 of 15	0 / 0	40

Commissions

Commissions open, DM codebottle on Discord (https://discord.com/users/320486798859960322). I build custom finetunes like this one: characters, product voices, distillation into smaller models, and domain or use-case specific models.

License

Apache-2.0, inherited from Google's Gemma 4 release.

Downloads last month: 30

Safetensors

Model size

31B params

Tensor type

BF16

F8_E4M3

Model tree for LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

LessThanThreeAI/Gemma-4-31B-Humanlike-Chat

Quantized

(4)

this model

LessThanThreeAI
/

Gemma-4-31B-Humanlike-Chat-FP8

Gemma-4-31B-Humanlike-Chat (FP8)

vLLM

Format

VRAM

Checks

Commissions

License

Model tree for LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8

Space using LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8 1