Xylolabs

Clairic Flash MLX 8-bit

Base model Format License Code

The language model of Cloudflare/clairic-flash (9B, Qwen3.5 architecture) converted to 8-bit MLX for mlx-lm; the vision tower and the scoring head of the original are not included.

How to run

pip install mlx-lm==0.32.2

mlx_lm.generate --model Xylolabs/clairic-flash-MLX-8bit --prompt 'Summarize the invoice: Northwind Supply, 2026-09-02, pens and paper, total $1080.00.'
mlx_lm.chat     --model Xylolabs/clairic-flash-MLX-8bit

Accuracy

Mean KL divergence from BF16 (lower is better) and top-1 agreement with BF16.

Quant Size WikiText-2 KL top-1 Chat KL top-1 Held-out KL top-1
MLX 8-bit 9.51 GB 0.001655 98.848% 0.004075 98.461% 0.000569 99.039%
Mean KL divergence by file size Top-1 agreement by file size

Which file for your hardware

Macs only (MLX runs on Apple silicon; memory options as Apple lists them for the Mac Studio, M5 Max 36, 48, 64 and 128 GB, M5 Ultra 96, 256 and 512 GB, and the 14-inch MacBook Pro M5 Max, checked 2026-11-22). The GPU may use about 75% of unified memory by default; sudo sysctl iogpu.wired_limit_mb=<MB> raises that limit (it resets at reboot). Fit rule: file + KV cache at the stated context + about 2 GB must fit in the GPU limit; sizes in GB (10^9 bytes); context is the longest that fits at the default limit, at least 32K. KV cache 33 KB per token (8 full-attention layers x 4 KV heads x 256 x 2 x 2 bytes; the other 24 layers keep a fixed 50 MB state). No MLX speed has been measured on these Macs.

Hardware Memory Recommended file (ours only) Context that fits Notes
Mac Studio M5 Max (also MacBook Pro 14-inch M5 Max, 32-core GPU) 36 GB unified Xylolabs/clairic-flash-MLX-8bit (8-bit, 9.53 GB) 256K (model maximum) Fits at the default GPU limit (75% of memory).
Mac Studio M5 Max (also MacBook Pro 14-inch M5 Max, 40-core GPU) 48 GB unified Xylolabs/clairic-flash-MLX-8bit (8-bit, 9.53 GB) 256K (model maximum) Fits at the default GPU limit (75% of memory).
Mac Studio M5 Max (also MacBook Pro 14-inch M5 Max, 40-core GPU) 64 GB unified Xylolabs/clairic-flash-MLX-8bit (8-bit, 9.53 GB) 256K (model maximum) Fits at the default GPU limit (75% of memory).
Mac Studio M5 Ultra 96 GB unified Xylolabs/clairic-flash-MLX-8bit (8-bit, 9.53 GB) 256K (model maximum) Fits at the default GPU limit (75% of memory).
Mac Studio M5 Max, 40-core GPU (also MacBook Pro 14-inch) 128 GB unified Xylolabs/clairic-flash-MLX-8bit (8-bit, 9.53 GB) 256K (model maximum) Fits at the default GPU limit (75% of memory).
Mac Studio M5 Ultra 256 GB unified Xylolabs/clairic-flash-MLX-8bit (8-bit, 9.53 GB) 256K (model maximum) Fits at the default GPU limit (75% of memory).
Mac Studio M5 Ultra, 80-core GPU 512 GB unified Xylolabs/clairic-flash-MLX-8bit (8-bit, 9.53 GB) 256K (model maximum) Fits at the default GPU limit (75% of memory).

License and notices

These files are under the Apache License 2.0, copied in LICENSE (Cloudflare's text); the original model is Cloudflare's, itself built on Qwen/Qwen3.5-9B (Apache-2.0). We quantized the language-model weights to MLX 8-bit with mlx-lm and left out the vision tower, the scoring head and the Python runtime. The source revision and what was changed are in ORIGINS.md and NOTICE. Not affiliated with or endorsed by Cloudflare.

Updates

  • 2026-11-22: Added a hardware recommendation table.
  • 2026-11-22: First release.

Cloudflare's original model description

Below is the model card of Cloudflare/clairic-flash (Apache-2.0), without its metadata header and unchanged.

Clairic Flash

Clairic Flash is a 9B multimodal model that turns a state and a schema of typed fields into structured answers. It supports text and image inputs, extraction, numerical estimation, and forecasting. Each field has its own value and scoring information; the response also reports input truncation and token usage.

See Clairic for the other model in the Clairic family.

Model

  • Base model: Qwen3.5-9B.
  • Inputs: a text or JSON state, optional images, and a mapping of field names to specifications.
  • Outputs: typed values, lists, nulls, estimates, and forecast paths.
  • Scoring: extraction confidence and null probabilities, plus optional quantiles for estimates.
  • Runtime: PyTorch and Transformers, with local Python request helpers.

Usage

Use Python 3.11 or later and install the packages listed in requirements.txt. Inference uses PyTorch and Transformers; xgrammar supplies schema constraints through a Transformers logits processor.

Download the repository, load the model and processor, and call systemone with a System One: Extract request.

import sys

from huggingface_hub import snapshot_download

path = snapshot_download("Cloudflare/clairic-flash")
sys.path.insert(0, path)
from clairic_model import load_release_model, systemone

model, processor = load_release_model(path, device="cuda")

response = systemone(
    model,
    processor,
    {
        "state": (
            "Invoice from Northwind Supply. Issued 2026-09-02. "
            "Items: Pens; Paper. Total: $1080.00."
        ),
        "fields": {
            "vendor": {"type": "text", "instructions": "The invoice vendor."},
            "total": {"type": "number", "decimals": 2},
            "issued": {"type": "date"},
            "items": {
                "type": "list",
                "items": "text",
                "instructions": "The purchased item names, in order.",
            },
        },
    },
)
print(response["answers"])

Images

Pass PIL images alongside the state. Embedded base64 image inputs are also accepted.

from PIL import Image

response = systemone(
    model,
    processor,
    {
        "state": "Read the attached receipt.",
        "images": [Image.open("receipt.png")],
        "fields": {
            "merchant": {"type": "text", "instructions": "The merchant name."},
            "total": {"type": "number", "decimals": 2},
        },
    },
)
print(response["answers"])

Estimates and forecasts

Declare a range for estimated values. Forecasts also specify a horizon and interval. Set include_quantiles to return the available quantiles.

response = systemone(
    model,
    processor,
    {
        "state": "Daily demand for the last seven days: 41, 45, 43, 47, 49, 46, 48.",
        "fields": {
            "next_day": {"type": "estimate", "min": 0, "max": 100},
            "next_three_days": {
                "type": "forecast",
                "min": 0,
                "max": 100,
                "horizon": 3,
                "interval": "day",
            },
        },
        "options": {"include_quantiles": True},
    },
)
print(response["answers"])

Input format

Field Description
model Optional clairic-flash or @cf/cloudflare/clairic-flash
state Source text; the Python helper serializes JSON values to text
images Optional PIL images or embedded base64 images
documents Optional embedded PDF data URIs or content_type / base64 objects
fields Mapping of output field names to typed specifications
reference_date Optional ISO date for relative date instructions
options.include_quantiles Include available estimate and forecast quantiles
options.return_state_text Include the retained source text in the response

Field specifications support text, number, date, time, datetime, duration, boolean, enum, object, list, compute, estimate, and forecast. instructions describes what to return. Numeric fields can specify units and rounding; lists declare their item schema; estimates and forecasts require bounds. nullable defaults to true. source_only: true selects literal printed numbers, dates, times, datetimes, or number/date lists. knowledge: true permits knowledge answers for text, numbers, and supported list children. compute selects the typed numeric head. Unsupported options and invalid combinations are rejected.

Embedded inputs are limited to 4 MiB each and 8 MiB combined. Images and rendered PDF pages share a four-image/page limit. Image rotation accepts 0, 90, 180, or 270 clockwise degrees after EXIF orientation. Remote media URLs are not accepted.

Response

systemone returns a dictionary with model, answers, truncated, and usage. Answers are keyed by the requested field names. Generated scalar extraction answers retain valid, complete, full-sequence confidence, and independently scored p_null. Uniquely matched text evidence includes character spans in state; image-only or ambiguous evidence has null spans. Lists preserve item order and duplicates. Estimates and forecasts include their typed values and, when requested, quantiles.

Scores are model probabilities and should be evaluated for the application's own acceptance thresholds. Inspect truncated and any answer completeness indicators before relying on a result.

Usage includes retries and supplemental work. The response model ID is clairic-flash. The Python API raises validation or request errors for invalid inputs, a queue-full error for simultaneous requests, and an inference error for failed generation. Use await model.predict_async(request) in an async application; cancellation drains owned work before admitting another request.

Files

File Purpose
model*.safetensors, model.safetensors.index.json, config.json Model weights and configuration
clair_head.safetensors, clair_head_config.json Typed output components
clairic_model.py and supporting Python modules Transformers loading and request handling
Tokenizer and processor files Text and image preprocessing
requirements.txt Python dependencies
LICENSE Apache-2.0 license

License

Released under the Apache-2.0 license.

Downloads last month
25
Safetensors
Model size
9B params
Tensor type
U32
ยท
F16
ยท
F32
ยท
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Xylolabs/clairic-flash-MLX-8bit

Finetuned
Qwen/Qwen3.5-9B
Quantized
(6)
this model

Collection including Xylolabs/clairic-flash-MLX-8bit