Sphaela

sphaela's activity

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

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 2 months ago

webhie/Qwen3.6-27B-int4-AutoRound-Code

4

#7 opened 3 months ago by

soyalemujica

New activity in sphaela/Qwen3.6-35B-A3B-AutoRound-GGUF 2 months ago

New high quality quants

🔥❤️ 3

1

#2 opened 2 months ago by

sphaela

Coherence issue

👍 2

12

#1 opened 3 months ago by

jesterb32

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 2 months ago

Which version can someone with a budget of only 16GB GPU use?

👍 1

1

#10 opened 2 months ago by

tooltd

KLD comparison

1

#9 opened 2 months ago by

timtianyang

New activity in sphaela/gemma-4-31B-it-AutoRound-GGUF 2 months ago

Any plans to re-quantize with your improved scheme?

2

#2 opened 3 months ago by

aoleg

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 2 months ago

New high quality quants for smaller schemes(Q2_K_S and so on)

❤️ 3

39

#4 opened 3 months ago by

sphaela

Could you please requantize qwen 35BA3B and Gemma 26B with your new better method

1

#8 opened 3 months ago by

mahfuud33

Qwen3.6-27B-AutoRound Q4_K_M good quality

❤️ 1

10

#2 opened 4 months ago by

tooltd

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 3 months ago

It seems that the model is broken at commit 360c06a.

4

#6 opened 3 months ago by

battataka

Curiosity about MTP size and performance for Q8_0

2

#5 opened 3 months ago by

jswiftie

New activity in sphaela/gemma-4-31B-it-AutoRound-GGUF 3 months ago

Did you use the --enable_alg_ext flag?

2

#1 opened 4 months ago by

nlisac

New activity in sphaela/gemma-4-E4B-it-AutoRound-GGUF 3 months ago

running "MIXED" gguf with latest llama.cpp gave this error:

1

#1 opened 4 months ago by

saadsafi

New activity in sphaela/gemma-4-26B-A4B-it-AutoRound-GGUF 3 months ago

gemma-4-26b-a4b-it-q5_k_m

1

#1 opened 4 months ago by

saadsafi

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 3 months ago

MTP support

14

#3 opened 4 months ago by

Throghar

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 4 months ago

Impressive

🤗 2

8

#1 opened 4 months ago by

Throghar

New activity in sphaela/gemma-4-26B-A4B-it-AutoRound-GGUF 4 months ago

gemma-4-26b-a4b-it-q5_k_m

1

#1 opened 4 months ago by

saadsafi

New activity in sphaela/gemma-4-E4B-it-AutoRound-GGUF 4 months ago

running "MIXED" gguf with latest llama.cpp gave this error:

1

#1 opened 4 months ago by

saadsafi

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 4 months ago

Impressive

🤗 2

8

#1 opened 4 months ago by

Throghar

Qwen3.6-27B-AutoRound Q4_K_M good quality

❤️ 1

10

#2 opened 4 months ago by

tooltd