🏗️ Building on HF

Lynn

nerkyor

AI & ML interests

Post-training Qwen models for coding and efficient reasoning. Full quantization tiers plus speculative decoding (MTP / DFlash2) weights for llama.cpp, vLLM, SGLang and NInfer.

Recent Activity

updated a model 3 days ago

nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer

updated a model 3 days ago

nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2

new activity 6 days ago

nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2:Please release GSQ-RCO quantization for this model to run on 16GB gpus

View all activity

Organizations

None yet

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 6 days ago

Please release GSQ-RCO quantization for this model to run on 16GB gpus

#16 opened 6 days ago by

pawajee

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer 7 days ago

Fatal error

#2 opened 7 days ago by

QBANIN

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 10 days ago

Compact name

#15 opened 10 days ago by

hermitdave

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 12 days ago

[Bug] DFlash2 with prefix caching produces repetitive output on repeated long-context requests

#8 opened 22 days ago by

Yongzheng

Q2/Q3 what doas that mean?

#10 opened 20 days ago by

kalle07

New activity in nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2 13 days ago

size GGUF Q2

#1 opened 17 days ago by

kalle07

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 16 days ago

[can you / how can i] do this on MoE models?

#13 opened 16 days ago by

unterminal

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 19 days ago

question on cpp coding

#11 opened 19 days ago by

wangyich100

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 20 days ago

The name is misleading

#9 opened 20 days ago by

TLL-faraz

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 22 days ago

Orcarouter uncensored version when?

#7 opened 22 days ago by

markgilonginus

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 24 days ago

Request for W8A16 Quantization

#5 opened 25 days ago by

SharkDiscord

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 25 days ago

need mlx support

#4 opened 25 days ago by

Cachedxxx

请求W4A16量化版本

#3 opened 26 days ago by

haibin0528

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 26 days ago

Nice

👍 1

#1 opened 28 days ago by

Vonarest

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer 26 days ago

Is it possible to release a version specifically for 16GB of VRAM?

#1 opened 27 days ago by

jian2023

New activity in nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 26 days ago

need mtp support Q4_K

#2 opened 26 days ago by

zzf520

New activity in nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUF 30 days ago

正在尝试你的dflash2专版，希望能带来惊喜

#5 opened about 1 month ago by

wenhuahua

New activity in nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-MTP-NVFP4 30 days ago

Qwen 3.8 flash next?

#1 opened about 1 month ago by

hfmefi69

New activity in nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUF about 1 month ago

SSM alpha and beta quantization for Q2-LynnStyle

#4 opened about 1 month ago by

Gen4536

Tested Q3 in coding problem and simple reasoning questions

#3 opened about 1 month ago by

Throghar