FluidInference / kev-0.8b-coreml

huggingface.co
Total runs: 219
24-hour runs: 27
7-day runs: 51
30-day runs: 219
Model's Last Updated: September 26 2026
text-classification

Introduction of kev-0.8b-coreml

Model Details of kev-0.8b-coreml

Kev-0.8B for Core ML

Core ML export of jaredpalmer/kev-0.8b (Jared Palmer, Apache-2.0): Kev's LoRA folded into Qwen/Qwen3.5-0.8B-Base in fp32 with Kev's own loader, plus Kev's pointer head. Kev answers questions about a piece of text (a state ): multiple choice, yes/no, or a score, with calibrated probabilities.

Files
Path What
fused/KevFused.mlpackage Multifunction package, weight-shared: fused_S<state>_P<packed>_B16_K16 for states of 32–384 tokens and up to 192 packed question tokens. One call reads the state and answers all of a request's questions (up to 16 answers, 16 options each).
fused/config.json Dimensions, special tokens, temperature.
L512_K16/KevRow_fp16.mlpackage One question per call (state + question ≤ 512 tokens, ≤ 16 options), for questions that do not fit the fused path.
L1024_K80/KevRow_fp16.mlpackage One question per call up to 1,024 tokens and 80 options (e.g. 77-way intent questions).
L512_K16/embeddings.f16 Token embeddings (fp16, 248,320 × 1,024), gathered on the host.
tokenizer.json Qwen3.5 tokenizer.

fp16, GPU ( cpuAndGPU ), iOS 18 / macOS 15. Swift: KevFastManager in FluidUse (own Qwen BPE tokenizer, exact against Hugging Face tokenizers).

How the fused call works

The state's tokens come first, then every question packed end to end. A segment mask keeps each question from seeing the others: it is the attention mask, the local decay of the Gated DeltaNet layers, and the triangle of their WY solve, so every question restarts from the state exactly as if it were its own row. Everything except the delta-rule core runs once over all positions.

Fidelity

Kev's own benchmark, unchanged, scored the row packages against Kev's fp32 PyTorch model on the development splits:

Suite Questions Top answer differs Kev fp32 Published Core ML fp16
transfer-v4 764 1 0.6479 0.648 0.6463
decision-v7 1,468 2 0.8267 0.827 0.8252

The fused pass matches the row form in fp32 (0 flips, max |Δp| 3e-6 with every question packed three times), and the fp16 fused functions agree with the fp16 row packages on 191 questions (0 flips, max |Δp| 0.004).

Speed and memory against the original model

MacBook Pro M5 Pro (24 GB). Guess Who over 80 Wikipedia people (DBpedia-14 test split): each bio is one request with 12 yes/no questions, 960 decisions. The original is Kev's own checkpoint loader and serving path in PyTorch on the GPU (MPS).

Core ML (this repo, fp16, GPU) Original, PyTorch bf16 Original, PyTorch fp32 (default)
80 bios × 12 questions 2.98 s 98.6 s 123.9 s
per bio (12 answers, one call) 36.6 ms 1,070 ms 1,287 ms
peak memory footprint 0.67 GB (+1.45 GB weights mapped from disk) 6.6 GB 9.5 GB
weights 1.45 GB (fused package + embeddings) 1.79 GB (bf16 base + LoRA/head) same
answers vs original fp32 0 of 960 differ 3 of 960 differ reference

PyTorch on a Mac runs Qwen3.5's Gated DeltaNet and causal conv through transformers' reference implementations (the flash-linear-attention / causal_conv1d kernels are not available there). Peak memory footprint is Activity Monitor's Memory; Core ML maps its weights from disk, so count them as resident for a conservative ~2.1 GB. This backbone does not suit the Neural Engine (one call: GPU 30.8 ms, CPU 186 ms, CPU + ANE 740 ms). A function left idle pays a 0.3–0.8 s re-setup on its next call; warm it before latency-sensitive work.

Conversion code and reports: FluidInference/mobius , models/computer-use/kev-0.8b/coreml .

Runs of FluidInference kev-0.8b-coreml on huggingface.co

219
Total runs
27
24-hour runs
49
3-day runs
51
7-day runs
219
30-day runs

More Information About kev-0.8b-coreml huggingface.co Model

More kev-0.8b-coreml license Visit here:

https://choosealicense.com/licenses/apache-2.0

kev-0.8b-coreml huggingface.co

kev-0.8b-coreml huggingface.co is an AI model on huggingface.co that provides kev-0.8b-coreml's model effect (), which can be used instantly with this FluidInference kev-0.8b-coreml model. huggingface.co supports a free trial of the kev-0.8b-coreml model, and also provides paid use of the kev-0.8b-coreml. Support call kev-0.8b-coreml model through api, including Node.js, Python, http.

FluidInference kev-0.8b-coreml online free

kev-0.8b-coreml huggingface.co is an online trial and call api platform, which integrates kev-0.8b-coreml's modeling effects, including api services, and provides a free online trial of kev-0.8b-coreml, you can try kev-0.8b-coreml online for free by clicking the link below.

FluidInference kev-0.8b-coreml online free url in huggingface.co:

https://huggingface.co/FluidInference/kev-0.8b-coreml

kev-0.8b-coreml install

kev-0.8b-coreml is an open source model from GitHub that offers a free installation service, and any user can find kev-0.8b-coreml on GitHub to install. At the same time, huggingface.co provides the effect of kev-0.8b-coreml install, users can directly use kev-0.8b-coreml installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

kev-0.8b-coreml install url in huggingface.co:

https://huggingface.co/FluidInference/kev-0.8b-coreml

Url of kev-0.8b-coreml

Provider of kev-0.8b-coreml huggingface.co

FluidInference
ORGANIZATIONS

Other API from FluidInference