Sponsored by
Crazyrouter
-The enterprise-grade, cost-effective AI API gateway that provides one API key to access 300+ AI models through OpenAI-compatible endpoints, with
Cloudflare's
clef-flash
, a 9B decision model post-trained from
Qwen3.5-9B
, converted to Core ML for Apple silicon.
Text only
, 8-bit
weights, runs on the Mac GPU.
Same contract as Clef and the Jev / SystemOne API: a
state
(text or JSON) and typed questions (
noul
yes/no,
choice
, ordered
score
) go in;
one probability for every allowed option of every question
comes out of a
single forward pass. Nothing is generated.
Runtime:
ClefFlashManager
in
FluidUse
(Swift, macOS 15+), with a
SwiftUI support-ticket triage demo (
ClefFlashDemo
).
Packages
File
Role
Size
Precision
part00
…
part07.mlpackage
Qwen3.5 decoder, 4 layers each (the last adds the final norm); functions
L256
L512
L1024
L2048
per sequence bucket, weights shared
6.5 GB total
8-bit weights (per channel), fp16 compute
Head.mlpackage
Clef's joint schema head, fixed shape: ≤ 16 questions, ≤ 96 options; same four functions
465 MB
fp32
embeddings.f16
input token embeddings (host-side gather)
2.0 GB
fp16
output_embeddings.f16
output embeddings, the head's lexical option rows (clef-flash does not tie them)
2.0 GB
fp16
tokenizer.json
,
config.json
tokenizer; shapes, buckets and token ids for the host
Each decoder part:
hidden [1, L, 4096]
,
cos
/
sin [L, 64]
(fp16) →
out [1, L, 4096]
. Text-only records use
positions
0..L-1
on all three M-RoPE axes. The host renders the record exactly like Clef's
encode_record
,
gathers embeddings, chains the 8 parts and builds the head's span-mean matrices; the Swift runtime is the reference
host. Images and video are not converted.
Quality
Reference: the same decoder in fp32 (matches Hugging Face's
Qwen3_5TextModel
to 5e-5 relative) streamed four
layers at a time, plus Cloudflare's own
JointSchemaHead
. 605 records / 611 questions (README samples, ARC-Easy and
ARC-Challenge test, first 300 each):
This model (8-bit Core ML)
fp32 reference
Cloudflare published
answers that differ from fp32
1 / 611 (a near-tie: fp32 top-2 within 0.005)
—
—
median probability difference
0.0004
—
—
ARC-Easy
100.0%
100.0%
99.5%
ARC-Challenge
99.0%
98.67%
98.3%
ARC rendering is Clef's record format with a plain state, not the Decision Index kit's templates, so compare within
about a point.
Speed (M5 Pro, 24 GB, GPU)
Median
one decoder part (4 layers), 512-token bucket
62 ms
one record, 3 questions, ~370 tokens (L512)
, Swift runtime
0.49 s
(p95 0.57 s)
load (compiled), 8 parts + head
~40 s
The decoder needs ~7 GB of memory to itself; with other large processes running it pages and slows down sharply.
The Qwen3.5 decoder (Gated DeltaNet layers) does not run on the Neural Engine: Core ML places 0 of its ops on the
ANE, so this is a GPU model.
Usage (Swift)
import FluidUse
let manager =tryawaitClefFlashManager.load(from: bundleDirectory, bucket: 512)
let result =tryawait manager.answer(
state: "Our checkout is down and customers can't pay.",
questions: [
("team", .choice(instructions: "Which team should handle this ticket?",
criteria: ["billing": "Charges, refunds", "engineering": "Bugs, outages"])),
("urgency", .score(instructions: "How urgent is this ticket?", criteria: ["Low", "Normal", "High", "Critical"])),
])
print(result.answers.map { ($0.questionID, $0.choice) }, result.totalMilliseconds)
License and credits
Apache-2.0, same as
Cloudflare/clef-flash
(
LICENSE
is
Cloudflare's). All model weights are Cloudflare's; this repository only changes their format and precision.
Conversion by
Fluid Inference
.
Runs of FluidInference clef-flash-coreml on huggingface.co
157
Total runs
0
24-hour runs
15
3-day runs
65
7-day runs
157
30-day runs
More Information About clef-flash-coreml huggingface.co Model
clef-flash-coreml huggingface.co is an AI model on huggingface.co that provides clef-flash-coreml's model effect (), which can be used instantly with this FluidInference clef-flash-coreml model. huggingface.co supports a free trial of the clef-flash-coreml model, and also provides paid use of the clef-flash-coreml. Support call clef-flash-coreml model through api, including Node.js, Python, http.
clef-flash-coreml huggingface.co is an online trial and call api platform, which integrates clef-flash-coreml's modeling effects, including api services, and provides a free online trial of clef-flash-coreml, you can try clef-flash-coreml online for free by clicking the link below.
FluidInference clef-flash-coreml online free url in huggingface.co:
clef-flash-coreml is an open source model from GitHub that offers a free installation service, and any user can find clef-flash-coreml on GitHub to install. At the same time, huggingface.co provides the effect of clef-flash-coreml install, users can directly use clef-flash-coreml installed effect in huggingface.co for debugging and trial. It also supports api for free installation.