Alireza Dadgarnia

anm2211's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 5 minutes ago

Abliterated PLS!

🔥 4

5

#15 opened 3 days ago by

Fndxxxx

New activity in ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ about 15 hours ago

GGUF for CPU inference

1

#2 opened 1 day ago by

tamilsabari

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF about 16 hours ago

DFlash2

🚀 1

2

#23 opened 1 day ago by

countofserenno

#Request: Would u consider moe gguf models at around 8-11gbs size with same quant and mtp overhead attached please?

1

#18 opened 2 days ago by

ahmedsevenup

authored a paper 1 day ago

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Paper • 2604.18556 • Published Apr 20 • 14

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 3 days ago

MLX version Please！

🚀 1

2

#9 opened 3 days ago by

greenerdalii

New activity in ISTA-DASLab/Qwen3.8-27B-3Bit-GSQ 5 days ago

Maybe add vLLM FP8 KVCache calibration scales?

4

#3 opened 8 days ago by

ibaldonl

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 6 days ago

request for qwen3.8 next

🚀 5

10

#3 opened 11 days ago by

Chillzyg

Would you consider GSQ-RCO IQ3_S + MTP for a Qwen3.8-27B coding-focused fine-tune?

🚀 1

6

#8 opened 7 days ago by

Schestex

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 7 days ago

It is recommended to use IQ3_S-MTP for better instruction following and programming capabilities.

👍🔥 15

6

#7 opened 8 days ago by

qwased

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 8 days ago

Mtp integrated version coming?

🚀 3

11

#4 opened 10 days ago by

CheesingGouda

New activity in ISTA-DASLab/Qwen3.8-27B-3Bit-GSQ 8 days ago

Plans to upstream this patch in vLLM?

1

#2 opened 8 days ago by

ibaldonl

New activity in ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ 8 days ago

can add gguf for us, please?

👍 1

1

#1 opened 8 days ago by

xizonghu

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 10 days ago

Request for standard Q-type quantizations (Q3_K_XL, Q4_K_M/XL) for AMD GPU compatibility

👀🚀 4

6

#5 opened 10 days ago by

myhugginfacegacc

New activity in ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF 11 days ago

Bigger version?

🚀 1

4

#2 opened 11 days ago by

smol-computer

Please keep the MTP/nextn tensors — and consider a ~3.25 bpw target

🧠➕ 8

4

#1 opened 12 days ago by

palmanza

updated a model 11 days ago

ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF

Image-Text-to-Text • 27B • Updated 8 days ago • 615k • 754

upvoted a paper 12 days ago

Model Compression with Exact Budget Constraints via Riemannian Manifolds

Paper • 2605.00649 • Published May 7 • 4

New activity in ISTA-DASLab/Qwen3.8-27B-3Bit-GSQ 14 days ago

This result is so exciting — has anyone done a full benchmark test on it?

👍 1

3

#1 opened 14 days ago by

modderbug

updated a collection 19 days ago

GSQ

Collection

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 10 items • Updated 19 days ago • 11