Collection of State-of-the-art FP8 Block Quantized Models
NM Testing
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
507
nm-testing/Llama-4-Maverick-17B-128E-Instruct-block-FP8
Text Generation
•
Updated
•
224
nm-testing/Qwen3-VL-235B-A22B-Instruct-FP8-BLOCK
Text Generation
•
Updated
•
35
nm-testing/Llama-4-Scout-17B-16E-Instruct-BLOCK-FP8
Text Generation
•
109B
•
Updated
•
31
nm-testing/Qwen3-30B-A3B-FP8-block
Text Generation
•
3B
•
Updated
•
27
nm-testing/tiny-testing-random-weights
584k
•
Updated
•
50
nm-testing/upload_test
Updated
nm-testing/Llama4-Maverick-Eagle3-Speculators-64k-vocab
Updated
•
32
nm-testing/Llama-3.1-8B-Instruct-KV-FP8-tensor-static_minmax
8B
•
Updated
•
35
nm-testing/Llama-3.1-8B-Instruct-QKV-FP8-attn_head-static_minmax
8B
•
Updated
•
13
nm-testing/Llama-3.1-8B-Instruct-KV-FP8-attn_head-static_minmax
8B
•
Updated
•
10