Initial Support for QWEN3
ANEMLL: Open Source project for TPU models
anemll
AI & ML interests
Apple Neural Engine, on-device-compute
Recent Activity
liked
a model
7 days ago
smpanaro/Qwen2.5-0.5B-4bit-PerTensor
updated
a model
8 days ago
anemll/anemll-dwq-llama-3.2-1B-4b-pf6b-ctx1024_0.3.0
updated
a model
8 days ago
anemll/anemll-Qwen3-0.6B-ctx512_0.3.0
Organizations
Just an EZ way to collect papers on HF
-
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 34 -
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Paper • 2503.04872 • Published • 15 -
FFN Fusion: Rethinking Sequential Computation in Large Language Models
Paper • 2503.18908 • Published • 19
Initial Support for QWEN3
Just an EZ way to collect papers on HF
-
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 34 -
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Paper • 2503.04872 • Published • 15 -
FFN Fusion: Rethinking Sequential Computation in Large Language Models
Paper • 2503.18908 • Published • 19
models
25
anemll/anemll-dwq-llama-3.2-1B-4b-pf6b-ctx1024_0.3.0
Updated
•
29
anemll/anemll-Qwen3-0.6B-ctx512_0.3.0
Updated
•
111
anemll/anemll-Qwen3-4B-ctx1024_0.3.0
Updated
•
178
•
1
anemll/anemll-Qwen3-1.7B-LUT6-ctx100
Updated
•
43
anemll/anemll-Qwen-Qwen3-0.6B-FP16-ctx512_0.3.3
Updated
•
5
anemll/anemll-Llama-3.2-1B-FAST-iOS_0.3.0
Updated
•
24
anemll/anemll-Nemo_full-8B-FP16-b64-w512
Updated
•
32
•
1
anemll/ANEMLL-Prefill-bench
Updated
anemll/anemll-hermes3b-LUT8_0.3.0
Updated
•
14
anemll/anemll-Meta-Llama-3.2-1B-LUT8_ctx512_0.3.0
Updated
•
40
•
1
datasets
0
None public yet