arxiv:2411.02355
Eldar Kurtić
ekurtic
AI & ML interests
Efficient inference
Recent Activity
updated
a model
about 16 hours ago
ekurtic/Llama-Guard-4-12B-quantized.w8a8
published
a model
about 17 hours ago
ekurtic/Llama-Guard-4-12B-quantized.w8a8
updated
a model
about 17 hours ago
ekurtic/Llama-Guard-4-12B-FP8-dynamic
Organizations
models
22
ekurtic/Llama-Guard-4-12B-quantized.w8a8
12B
•
Updated
ekurtic/Llama-Guard-4-12B-FP8-dynamic
12B
•
Updated
ekurtic/Qwen3-32B-ll_bsearch_kl0.005_eap0.985_sha_bw5.34_4-8bit_grouped_seed42
17B
•
Updated
•
8
ekurtic/Qwen3-32B-ll_bsearch_kl0.005_eap0.99_sha_bw6.44_4-8bit_grouped_seed42
17B
•
Updated
•
5
ekurtic/fake_eldar_Llama-3.3-70B-Instruct_asym
11B
•
Updated
•
3
ekurtic/fake_eldar_Llama-3.3-70B-Instruct_sym
11B
•
Updated
•
5
ekurtic/lossless-lm-dev-uniform-bw4
Updated
ekurtic/Qwen3-8B-kvattn-fp8-tensor
8B
•
Updated
•
11
ekurtic/Qwen3-8B-kvattn-fp8-attn_head
8B
•
Updated
•
8
ekurtic/Llama-3.1-8B-Instruct-kvattn-fp8-tensor
8B
•
Updated
•
9
datasets
0
None public yet