REEEEEK
qenme
·
AI & ML interests
None yet
Recent Activity
new activity about 6 hours ago
cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4:Potential 5 layers that can be int8 updated a model 5 days ago
qenme/jina-ocr-v1-Q8_0-mtp-gguf published a model 5 days ago
qenme/jina-ocr-v1-Q8_0-mtp-ggufOrganizations
None yet
Potential 5 layers that can be int8
#2 opened about 8 hours ago
by
qenme
Jina llamacpp with MTP
#4 opened 5 days ago
by
qenme
🚩 Report: Spam
🤝 2
4
#7 opened 3 months ago
by
abaragambi
Running Qwen3.8-Flash-Next-AWQ-INT4
12
#1 opened about 1 month ago
by
cpatonn
Backend tokenizer issue due to "transformers_version": "5.16.0.dev0"
11
#2 opened about 1 month ago
by
qenme
Tokenizer changed to "tokenizer_class": "Qwen2Tokenizer"?
#108 opened about 1 month ago
by
qenme
Glad to see!
1
#1 opened about 1 month ago
by
qenme
pp sucks
8
#14 opened about 2 months ago
by
gopi87
Bad name?
3
#12 opened about 2 months ago
by
qenme
Are you actively using this?
2
#1 opened about 2 months ago
by
qenme
Any plans to release perplexity and KLD numbers?
👍 1
#21 opened 2 months ago
by
qenme
Possible bugs in `UD-Q6_K_XL`
1
#20 opened 2 months ago
by
auf1r2
"I used to pray for times like these"
🔥❤️ 5
1
#28 opened 2 months ago
by
Kuberwastaken
Very bad results with model quant and KV cache quant, only BF16 works well
👍👀 6
5
#34 opened 5 months ago
by
qenme
Something is broken
9
#12 opened 2 months ago
by
qenme
Sampler Settings?
👀 1
9
#8 opened 2 months ago
by
pegasus912
What is the point of this model?
👀 1
2
#2 opened 2 months ago
by
ChessVania
nice work man
1
#3 opened 3 months ago
by
qenme
Q4_X on Blackwell + EPYC + DDR 5
👍🔥 4
13
#3 opened 5 months ago
by
sousekd