Mathieu GELI
gelim
·
AI & ML interests
AI, Security
Organizations
None yet
NVFP4 vs FP8 throughput on an RTX 6000 Pro 96 GB (Blackwell) - real vLLM numbers
❤️👍 3
2
#9 opened 3 months ago
by
janreges3
Q4_K_M on 3 Tesla V100 (32GB) + ts-bench
👍 1
2
#5 opened 3 months ago
by
gelim
Where is the gguf?
4
#1 opened 5 months ago
by
OracleToes
Thank you!
👍 6
16
#1 opened 8 months ago
by
anikifoss
smol-IQ2_XS is a damn good quant!
👍🔥 7
7
#2 opened 8 months ago
by
tarruda
image support
🧠👀 12
9
#9 opened over 1 year ago
by
kuliev-vitaly
Perplexity on Q6_K
👍 1
1
#2 opened over 1 year ago
by
gelim