Install & run this model easily using llmpm
#30 opened about 1 month ago
by 
sarthak-saxena
Regarding RoPE frequency
#29 opened about 2 months ago
by 
juneyongyang
Add GPQA evaluation result
โค๏ธ 2
#28 opened 3 months ago
by 
burtenshaw
๐ฆ **่ด Qwen3๏ผ่ฐข่ฐขไฝ ๆไธบโๆ่่ โ็ๅบ็ณ**
โค๏ธ 1
#27 opened 3 months ago
by 
aifeifei798
Lora Fine Tning- Several Issues
3
#25 opened 5 months ago
by 
aetherforge
RTX 5090 + Qwen 30B MoE @ 135 tok/s in NVFP4 Guide
#24 opened 5 months ago
by 
JohnTdi
Error when utilizing DUAL_CHUNK_FLASH_ATTN with vLLM.
1
#23 opened 6 months ago
by 
lssj14
Can I enable DCA on other qwen3 dense models?
#22 opened 7 months ago
by 
dophys
Update README.md
#18 opened 8 months ago
by 
Brokersponsor
Polish language support
#17 opened 8 months ago
by 
eXt73
Working GPTQ-Int4 version?
๐ 1
#15 opened 8 months ago
by 
koesn
fix: max tokens to 1M
#14 opened 8 months ago
by 
heitormsb
help: 1M context error?
#13 opened 8 months ago
by heitormsb
ๅ ณไบ static KV-Cache(ValueError: This model does not support cache_implementation='static')
#11 opened 9 months ago
by 
luohuashijieyoufengjun
Upload 17F9CDA2-7E35-4793-9D18-0581B0276089.jpeg
1
#10 opened 9 months ago
by 
Faragcg
Test Scores Can Be Misleading
๐ 1
8
#8 opened 9 months ago
by 
phil111
Qwen3-30B-A3B-Instruct-2507-Autoround-Int-4bit-gptq
๐ฅ๐ 2
1
#7 opened 9 months ago
by 
jart25
Remove trailing tabs after license to avoid mlx_lm.convert errors
#6 opened 9 months ago
by 
Gallardo994
Local Installation Video and Testing - Step by Step
#5 opened 9 months ago
by 
fahdmirzac
Is the base model of the this model Qwen3-30B-A3B๏ผ
โ 4
#4 opened 9 months ago
by 
paulcx
AWQ version
โค๏ธ 6
6
#3 opened 9 months ago
by 
devops724
An Improvement, But Q3 30b Still Has Very Little General Knowledge
โค๏ธ๐ 3
11
#2 opened 9 months ago
by phil111
THANK YOU QWEN! ๐
๐โค๏ธ 10
1
#1 opened 9 months ago
by 
AyyYOO