Resources

Qwen3-Coder-Next GGUF Benchmarks!

pinned

👍 3

#20 opened about 2 months ago by

danielhanchen

Feb 19: Qwen3-Coder-Next GGUFs update - much better outputs!

pinned

🤗👍 16

#5 opened 2 months ago by

danielhanchen

Android Studio issue with Qwen3-Coder-Next-GGUF

#28 opened 14 days ago by

DocWolle

Model load in gpu & ram but only CPU compute is used

#27 opened 27 days ago by

klaasb123

Agent Response missing at the end in prompt/chat template? Looping end.

#26 opened about 1 month ago by

chrisoutwright

Install & run this model easily using llmpm

#25 opened about 1 month ago by

sarthak-saxena

Issue with OpenCode

#24 opened about 1 month ago by

Gogich77

Request for update

🤝➕ 4

#23 opened about 2 months ago by

engrtipusultan

Error on Ollama | 3 bit quantized | 500 Internal Server Error

#22 opened about 2 months ago by

Sidmttl

MXFP4 slower than Q4_K_M

#21 opened about 2 months ago by

ykarout

TQ1_0 quants

🔥 2

#19 opened about 2 months ago by

ilintar

Built a platform to deploy AI models instantly. Looking for feedback from ML engineers

#18 opened about 2 months ago by

jensenjesper

GGUF Update (17 Feb)

👀 5

#17 opened about 2 months ago by

allkhor

Ablation studies on effects of quantization on SSM weights?

#15 opened 2 months ago by

dinerburger

Feb 13 update? I have Feb 4, should I update?

👀 9

#14 opened 2 months ago by

tnuvkeg

UD-Q4_K_XL lower precision than Q4_K_M?

#12 opened 2 months ago by

zhuangzhoumengdie

Qwen3-Coder-Next-IQ4_NL.gguf tool calling issue. - Update: SOLVED

#11 opened 2 months ago by

robert1968

Publish KL-Divergence for Every Quant Level, for all your models

➕ 15

#10 opened 2 months ago by

BitBuilder

UD-Q5_K_XL not recognized

#9 opened 2 months ago by

Metalazzo

does not work with ollama 0.15.5 - 0.15.6

#8 opened 2 months ago by

asg345asdf

stepfun 3.5 flash pls

#7 opened 2 months ago by

Simon716

Inquiry About Unsloth Dynamic 1.8-bit Qwen3-Coder-Next-UD-TQ1_0.gguf for vLLM Deployment

#6 opened 2 months ago by

BuiDoan

just curious, why the lack of <thinking> response?

#4 opened 2 months ago by

YellowjacketGames

What are the differences between MFxP4, Q4, and UD-Q4 quantization? Which one is better to use on an AMD 395?

👍 8

#3 opened 2 months ago by

wszgrcy

Error jinja template LM Studio + Open Code or Qwen code or Kilo Code

#2 opened 2 months ago by

RGMC98

Check in here for tok/s and benchmarks for local gguf models

👍 1

#1 opened 2 months ago by

ykarout