Henkie Tenkie

HenkTenk

·

AI & ML interests

None yet

Organizations

None yet

New activity in cyankiwi/Qwen3.6-27B-AWQ-BF16-INT8 2 months ago

Compatible with vLLM on Ampere?

#3 opened 2 months ago by

New activity in cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4 2 months ago

What is the update ?

#4 opened 3 months ago by

New activity in Qwen/Qwen3.6-27B-FP8 3 months ago

Garbage output

#8 opened 3 months ago by

New activity in QuantTrio/Qwen3.6-35B-A3B-AWQ 3 months ago

PPLX or KLD, or other benchmark

#4 opened 3 months ago by

New activity in cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit 3 months ago

How does this compare to the original 8bit qwen quant and the 4 bit auto-round quant?

#5 opened 3 months ago by

New activity in cyankiwi/GLM-4.6V-AWQ-4bit 5 months ago

Can't seem to correctly generate structured output

#3 opened 7 months ago by

New activity in cyankiwi/GLM-4.5-Air-AWQ-4bit 6 months ago

Running on 6 GPUs

#10 opened 9 months ago by

KV Cache per token and Doubling the context size

#12 opened 6 months ago by

New activity in cyankiwi/Devstral-2-123B-Instruct-2512-AWQ-4bit 7 months ago

Unable to use on 4x3090

#4 opened 7 months ago by

New activity in cyankiwi/GLM-4.5-Air-AWQ-4bit 7 months ago

Running on 4 GPUs with TP=4

#11 opened 8 months ago by

New activity in cyankiwi/Devstral-2-123B-Instruct-2512-AWQ-4bit 7 months ago

Duplicate files

#3 opened 8 months ago by

New activity in cyankiwi/GLM-4.5-Air-AWQ-4bit 11 months ago

Improved useability

#7 opened 11 months ago by

New activity in gghfez/c4ai-command-a-03-2025-AWQ 11 months ago

Newest vLLM produces nonsense with longer context

#1 opened 11 months ago by

New activity in cyankiwi/GLM-4.5-Air-AWQ-4bit 11 months ago

Does this actually work with VLLM?

#1 opened 12 months ago by