L

lovedheart's activity

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

New activity in lovedheart/Qwen-AgentWorld-35B-A3B-FP8 about 2 months ago

Share quant script

1

#2 opened about 2 months ago by

verdverm

You didn't quantize it, did you? FP8 can't be the same size as BF16.

1

#1 opened about 2 months ago by

lsm03624

New activity in lovedheart/DeepSeek-V4-Flash-Lite-fastllm-Q2-Q3-Q4-Mixed about 2 months ago

CPU only goes ERROR，Model may be not used

2

#2 opened about 2 months ago by

Leeonne

New activity in inclusionAI/LLaDA2.0-Uni 4 months ago

Update README.md

#4 opened 4 months ago by

lovedheart

New activity in lovedheart/Qwen3-Coder-Next-REAP-48B-A3B-GGUF 6 months ago

REAM instead of REAP

3

#8 opened 6 months ago by

TomLucidor

Any hope to have Qwen3-Coder-Next-REAP-48B-A3B in non-gguf size?

2

#7 opened 6 months ago by

Mattepiu

There's a `vectorized key_gdiff`calculation bug in the Base Model.

1

#5 opened 6 months ago by

toby1991

Thanks for sharing, Q4_K_XL works great in OpenClaw

2

#4 opened 6 months ago by

toby1991

Qwen3-Next-REAP-48B

1

#3 opened 6 months ago by

KnutJaegersberg

iMatrix quants

2

#2 opened 6 months ago by

smcleod

Request: Qwen3-Coder-Next REAP variant with ~20% pruning

2

#1 opened 7 months ago by

rodrigomt

New activity in lovedheart/Qwen3-Next-REAP-40B-A3B-Instruct-GGUF 7 months ago

quantification loss？

1

#1 opened 7 months ago by

one903045

New activity in lovedheart/Qwen3-Next-REAP-40B-A3B-Thinking-GGUF 7 months ago

Many thanks for REAP version! Do you plan INSTRUCT REAP also?

1

#1 opened 7 months ago by

robert1968

New activity in unsloth/DeepSeek-V3.1-GGUF 12 months ago

Please upload the Q8_0 variant.

6

#3 opened 12 months ago by

newsletter

New activity in Qwen/Qwen3-235B-A22B-GGUF over 1 year ago

IQ4_XS for 128GB Macs

1

#1 opened over 1 year ago by

tarruda