John Leimgruber III PRO

ubergarm's activity

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

New activity in ubergarm/GLM-5.1-GGUF about 15 hours ago

GLM 5.1 vs GLM 5 - burns A LOT output tokens on thinking

👍 1

30

#6 opened 3 days ago by

curiouspp8

New activity in tarruda/Qwen3.5-397B-A17B-GGUF about 16 hours ago

What are your tokens/s? And what about rewriting MiniMax m2.7? Great work man!

3

#2 opened 1 day ago by

Arkovski

New activity in ubergarm/MiniMax-M2.7-GGUF about 16 hours ago

Quick bench for smol-IQ3_KS on 2 GPUs

👍 1

7

#4 opened 2 days ago by

curiouspp8

New activity in ubergarm/MiniMax-M2.7-GGUF about 22 hours ago

IQ4_XS vs IQ4_KSS

1

#7 opened 1 day ago by

Arkovski

New activity in zai-org/GLM-5.1 about 24 hours ago

Quantization

10

#5 opened 7 days ago by

NukeNotNull

New activity in ubergarm/MiniMax-M2.7-GGUF 1 day ago

Quick bench for IQ2_KS on 1 GPU

👍 1

5

#3 opened 2 days ago by

curiouspp8

4bpw request =)

👀 1

13

#2 opened 2 days ago by

BahamutRU

New activity in ubergarm/GLM-5.1-GGUF 1 day ago

Testing IQ3_KS

🚀 1

10

#3 opened 5 days ago by

shewin

New activity in ubergarm/MiniMax-M2.7-GGUF 1 day ago

Curious how Q2_K 75 GB compares to unsloth UD-Q2_K_XL 75.3 GB?

3

#6 opened 2 days ago by

ha1ry

4 bpw suggestions

👀 1

16

#1 opened 2 days ago by

ndroidph

New activity in ubergarm/MiniMax-M2.7-GGUF 2 days ago

What quant would be closest to AWQ?

1

#5 opened 2 days ago by

curiouspp8

New activity in sokann/GLM-5-GGUF-1.594bpw 2 days ago

Great job!

🤗 1

4

#2 opened 3 days ago by

ubergarm

New activity in ubergarm/GLM-5.1-GGUF 3 days ago

Testing smol-IQ4_K

6

#4 opened 4 days ago by

shewin

New activity in ubergarm/GLM-5.1-GGUF 4 days ago

Comparing against Unsloth UD_Q4_K_XL

👀 1

3

#5 opened 4 days ago by

TimothyRoo

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 4 days ago

Testing smol-IQ5_KS

4

#13 opened 4 days ago by

shewin

New activity in ubergarm/GLM-5.1-GGUF 4 days ago

Typical GLM 5.1 overhead on top of weights memory

👍 1

4

#2 opened 6 days ago by

curiouspp8

New activity in ubergarm/DeepSeek-V3.2-Speciale-GGUF 5 days ago

gguf_init_from_file_impl: tensor 'token_embd.weight' has invalid ggml type 139 (NONE)

3

#3 opened 3 months ago by

issa54

New activity in ubergarm/GLM-5.1-GGUF 6 days ago

Fantastic as usual

❤️ 5

5

#1 opened 7 days ago by

ndroidph

New activity in ubergarm/GLM-5-GGUF 7 days ago

Unreleased

5

#6 opened 20 days ago by

jpsequeira

New activity in ubergarm/Qwen3.5-27B-GGUF 8 days ago

Insight into the "weird" data.

145

#3 opened about 2 months ago by

espen96