A 0.70B-parameter
text decision model
for Apple silicon, distilled from Cloudflare's
clef-flash
(9B) into
Qwen3-0.6B
plus Clef's joint schema head. Same contract as Clef and the Jev / SystemOne API: a
state
and typed questions
(
noul
,
choice
,
score
) in, a probability for every option of every question out, one forward pass.
Runs on the GPU or
100% on the Neural Engine
(every decoder op placed on the ANE at all four buckets). PyTorch weights:
FluidInference/clef-text-0.6b
. Swift runtime:
ClefTextManager
in
FluidUse
.
joint schema head, fp16, ≤ 16 questions / ≤ 96 options, same four functions
197 MB
embeddings.f16
token embeddings (tied: also the head's lexical option rows)
297 MB
tokenizer.json
,
config.json
tokenizer; shapes and ids for the host
Decoder inputs:
hidden [1, L, 1024]
,
cos
/
sin [L, 128]
, additive causal
mask [1, 1, L, L]
(all fp16) →
states [1, L, 1024]
.
Quality
Held-out test splits (official test / validation sets, 5,124 questions), gold accuracy:
Task
this model
clef-flash 9B (teacher)
DBpedia-14 entity type
99.7
100.0
AG News topic
90.7
92.0
SST-2 sentiment
90.0
94.0
BANKING77 intent (77-way)
86.4
94.5
TweetEval offensive
85.0
82.3
Yelp stars (5-way)
69.0
70.7
Emotion (6-way)
68.0
58.0
BoolQ
82.3
90.7
MNLI
72.3
84.3
ARC-Easy
80.0
100.0
CommonsenseQA
65.0
94.3
ARC-Challenge
60.7
97.3
all
79.1
88.2
Good at routing and classification (within 0–4 points of the teacher on topic, entity, sentiment, rating, toxicity,
emotion);
not
a knowledge model — science / commonsense QA and NLI stay well below the 9B. Teacher agreement
86.4%, calibration ECE 0.046 (dev).
Core ML on the Neural Engine vs the PyTorch student on the same 5,118 test questions: 15 different answers (0.3%,
all near-ties: PyTorch top-2 within 0.11), median probability drift 0.013, gold accuracy equal within ±0.7 per task.
Speed (M5 Pro)
Decoder at 512 tokens:
35 ms on the GPU
(
.cpuAndGPU
), 64 ms on the Neural Engine (
.cpuAndNeuralEngine
),
200 ms CPU-only. On this Mac the GPU is ~2× faster; the Neural Engine leaves the GPU free for other work.
Bucket
Neural Engine, decoder + head
256 tokens
29 ms
512 tokens
69 ms
1,024 tokens
196 ms
2,048 tokens
591 ms
Swift runtime, 3-question support ticket (
370 tokens): **
48 ms on the GPU** (1,000 tickets in 57 s in the FluidUse
demo), ~77 ms on the Neural Engine — vs ~0.5 s for
clef-flash Core ML
(9B, GPU).
Training
24,208 records from 12 public datasets (train splits; test splits held out) labelled by clef-flash (8-bit Core ML,
1 flip / 611 vs fp32), KL (T = 2) + 0.3 gold cross-entropy, LoRA r64 on the backbone + full head, 2 epochs. The head
starts from clef-flash's head weights wherever the shapes match.
clef-text-0.6b-coreml huggingface.co is an AI model on huggingface.co that provides clef-text-0.6b-coreml's model effect (), which can be used instantly with this FluidInference clef-text-0.6b-coreml model. huggingface.co supports a free trial of the clef-text-0.6b-coreml model, and also provides paid use of the clef-text-0.6b-coreml. Support call clef-text-0.6b-coreml model through api, including Node.js, Python, http.
clef-text-0.6b-coreml huggingface.co is an online trial and call api platform, which integrates clef-text-0.6b-coreml's modeling effects, including api services, and provides a free online trial of clef-text-0.6b-coreml, you can try clef-text-0.6b-coreml online for free by clicking the link below.
FluidInference clef-text-0.6b-coreml online free url in huggingface.co:
clef-text-0.6b-coreml is an open source model from GitHub that offers a free installation service, and any user can find clef-text-0.6b-coreml on GitHub to install. At the same time, huggingface.co provides the effect of clef-text-0.6b-coreml install, users can directly use clef-text-0.6b-coreml installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
clef-text-0.6b-coreml install url in huggingface.co: