How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rmonsurate/Maple")
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("rmonsurate/Maple")
model = AutoModelForMultimodalLM.from_pretrained("rmonsurate/Maple", 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]:]))
Quick Links

Maple

Maple is a Canadian-first assistant model from Farpoint Technologies, a Canadian company. It is a fine-tune of Victoria, our compressed 4-bit coding and agent model, which was itself cut down and retrained from a larger open-weight model (see Licence and attribution).

When an everyday question about tax, employment, benefits, immigration, health or housing does not name a country, Maple answers in Canadian terms by default. Given a web search tool, it looks things up and cites official Canadian sources. It also knows Canadian culture and answers in a polite Canadian tone, while still respecting a different jurisdiction when the user names one.

Maple is an NVFP4 model for vLLM on NVIDIA Blackwell GPUs, with 5.9B active parameters per token. SHA256SUMS lists the sha256 of every model file.

Results

Everyday questions that do not name a country. An answer passes if it is framed in Canadian terms, answers the question directly, is correct against an official source, and covers the key caveats. A question with no answer counts as a fail. Scores are the average of two AI judges.

Held-out test set (600 questions never seen in training)

Answered and passed the full standard Victoria Maple
With web search 6.6% 21.8%
Without search 1.3% 7.5%

With search, the gain is +15.2 points (95% CI +12.8 to +17.6). Without search, it is +6.2 points (95% CI +4.8 to +7.8).

Dev set only: comparison with the original full-size model

Dev set, without search Victoria Maple Original full-size model
Everyday questions (200): answered and passed 1.7% 10.8% 8.6%
Everyday questions: no answer 19.0% 17.5% 1.0%
Canadian culture (100, multiple choice): answered correctly 59% 77% 98%

"Original full-size model" is the uncompressed model Victoria was built from, named under Licence and attribution.

Caveats:

  • All results are AI-judged; no human grading has been done yet.
  • The comparison with the original full-size model is on the dev set only and is not comparable with the held-out table above.
  • The original full-size model is much stronger on Canadian culture and almost always gives an answer; Maple leads on answering an unmarked everyday question in Canadian terms to the full standard.

Quick start

hf download rmonsurate/Maple --local-dir maple

NVFP4 on vLLM, one NVIDIA Blackwell GPU (B300 or B200), draft head on:

vllm serve ./maple \
  --served-model-name maple \
  --tensor-parallel-size 1 \
  --max-model-len 20480 \
  --max-num-seqs 16 \
  --max-num-batched-tokens 16384 \
  --gpu-memory-utilization 0.80 \
  --enable-prefix-caching \
  --compilation-config '{"inductor_compile_config":{"triton.autotune_at_compile_time":false}}' \
  --kernel-config '{"enable_flashinfer_autotune":false}' \
  --trust-remote-code \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder \
  --reasoning-parser qwen3 \
  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
  • The --compilation-config line is required: compile-time Triton autotuning on this model either hangs or blows out startup time.
  • We ran vLLM from the upstream vLLM image for the original model, with two fixes backported for a prefix-caching crash on this architecture (vllm#53798 and vllm#54076). On a vLLM without those fixes, leave out --enable-prefix-caching.
  • Recommended sampling: thinking on, temperature 0.6, top_p 0.95, top_k 20.
  • Give the model a web search tool. Its Canadian-first habit is strongest when it can look things up.

There is no GGUF build of Maple.

Acknowledgements

Built on an 8x NVIDIA B300 system provided by Dell. Thanks to the Qwen team for the original model and to the maintainers of vLLM.

Licence and attribution

Maple is a fine-tune of Victoria, which is a modified version of Qwen3.8-Flash-Next, an open-weight model released by Qwen. Maple is distributed under the same licence as the original, the Qwen Community License 1.0. The full text, including Qwen's copyright notice, ships in this repo as LICENSE and must be kept with every copy.

Two further conditions in that licence pass on to anyone who uses Maple:

  • A licensee running a Model as a Service or AI Work Assistant business must obtain a separate license from Qwen before any commercial use.
  • A commercial product or service with more than 100,000,000 monthly active users or US$20,000,000 monthly revenue must display the model name prominently in its user interface.

Attribution goes to Qwen for Qwen3.8-Flash-Next and to Farpoint Technologies for Victoria and Maple.

Downloads last month
113
Safetensors
Model size
130B params
Tensor type
I64
ยท
BF16
ยท
F32
ยท
F8_E4M3
ยท
U8
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support