3 1 2

ANEMLL: Open Source project for TPU models

anemll

https://www.Anemll.com

AI & ML interests

Apple Neural Engine, on-device-compute

Recent Activity

new activity 4 days ago

google/gemma-3-1b-it-qat-int4-unquantized:is this per-channel int4 quantized?

updated a model 7 days ago

anemll/anemll-dwq-llama-3.2-1B-4b-pf6b-ctx1024_0.3.0

published a model 7 days ago

anemll/anemll-dwq-llama-3.2-1B-4b-pf6b-ctx1024_0.3.0

View all activity

Organizations

None yet

Collections 4

spaces 1

Running

On-Device LLM Throughput Calculator

🚀

Generate throughput plots for LLMs on devices

models 21

datasets 0

None public yet

ANEMLL: Open Source project for TPU models

AI & ML interests

Recent Activity

Organizations

Collections 4

Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation

FFN Fusion: Rethinking Sequential Computation in Large Language Models

anemll/anemll-llama-3.2-1B-iOSv2.0

anemll/anemll-DeepSeek_ctx1024_iOS.0.1.2

anemll/anemll-Hermes-3.2-3B-iOS-0.1.1

anemll/anemll-LLAMA-3.2-3B_ctx1024_LUT8_iOS

spaces 1

On-Device LLM Throughput Calculator

models 21

anemll/anemll-dwq-llama-3.2-1B-4b-pf6b-ctx1024_0.3.0

anemll/anemll-Nemo_full-8B-FP16-b64-w512

anemll/ANEMLL-Prefill-bench

anemll/anemll-hermes3b-LUT8_0.3.0

anemll/anemll-Meta-Llama-3.2-1B-LUT8_ctx512_0.3.0

anemll/anemll-DeepHermes-3.2-3B-ctx1024-LUT4_iOS

anemll/anemll-Llama-3.2-1B-FP16-iOS

anemll/anemll-Llama-3.2-1B-FAST-iOS_0.3.0

anemll/anemll-LLAMA-3.2-3B_ctx1024_LUT8_iOS

anemll/anemll-DeepSeek_ctx1024_iOS.0.1.2

datasets 0

ANEMLL: Open Source project for TPU models

AI & ML interests

Recent Activity

Organizations

Collections 4

spaces 1

On-Device LLM Throughput Calculator

models 21 Sort: Recently updated

datasets 0

models 21