Victor C.

dehnhaide's activity

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

New activity in stepfun-ai/Step-3.5-Flash-Base-Midtrain about 1 hour ago

Question about benchmark results

🔥🚀 2

8

#5 opened about 1 month ago by

tarruda

New activity in MiniMaxAI/MiniMax-M2.7 about 5 hours ago

Need a 5% and 15% REAP

7

#10 opened about 16 hours ago by

nawoalanor

New activity in ubergarm/GLM-5.1-GGUF about 5 hours ago

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

👍 1

21

#6 opened 1 day ago by

curiouspp8

New activity in mratsim/MiniMax-M2.5-FP8-INT4-AWQ about 7 hours ago

Hoping for your magic on MiniMax-M2.7-FP8-INT4-AWQ quant

8

#2 opened about 11 hours ago by

dehnhaide

New activity in MiniMaxAI/MiniMax-M2.7 about 11 hours ago

GGUF quants available — all sizes Q2_K through Q8_0 + BF16

🚀❤️ 1

2

#8 opened about 17 hours ago by

dennny123

New activity in AesSedai/MiniMax-M2.5-GGUF about 13 hours ago

I'm on waiting list for AesSedai Minimax M2.7 Q4_K_M or similar...

❤️ 1

4

#3 opened 24 days ago by

MartinPatterson

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 2 days ago

Testing smol-IQ5_KS

4

#13 opened 2 days ago by

shewin

New activity in google/gemma-4-31B-it 5 days ago

Model seems to have issues in vLLM (characters duplication)

🔥 1

8

#15 opened 9 days ago by

dehnhaide

New activity in ubergarm/Qwen3.5-397B-A17B-GGUF 9 days ago

Check out Thireus GGUF-Tool-Suite quants!

❤️🤗 5

8

#13 opened 9 days ago by

ubergarm

New activity in cyankiwi/gemma-4-31B-it-AWQ-8bit 9 days ago

Quant HAS issues + results with vLLM on 8x 3090

4

#1 opened 9 days ago by

dehnhaide

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 10 days ago

accuracy

26

#4 opened about 2 months ago by

ktsaou

New activity in AesSedai/Qwen3.5-397B-A17B-GGUF 15 days ago

Offloading layers is not working for me

9

#9 opened 19 days ago by

tnuvkeg

New activity in AesSedai/Kimi-K2.5-GGUF 15 days ago

AesSedai/Kimi-K2.5-GGUF using the Q4_X on 8 RTX 3090

🚀 1

12

#7 opened 16 days ago by

martossien

New activity in cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit 16 days ago

The RTX3090 works very well，ths！

❤️👍 4

3

#2 opened 27 days ago by

summerbuild

New activity in AesSedai/Step-3.5-Flash-Base-Midtrain-GGUF 17 days ago

Yet another excellent quant suite from AesSedai

#1 opened 17 days ago by

dehnhaide

New activity in NeuroSenko/Qwen3.5-397B-A17B-exl3 19 days ago

Tool calling

7

#1 opened 22 days ago by

dehnhaide

New activity in cyankiwi/Mistral-Small-4-119B-2603-AWQ-4bit 19 days ago

duplicated tensor files

2

#1 opened 25 days ago by

ak1020

New activity in Intel/Qwen3.5-397B-A17B-gguf-q2ks-mixed-AutoRound 19 days ago

Performance indicators

👍 2

4

#1 opened 19 days ago by

dehnhaide

New activity in mistralai/Mistral-Small-4-119B-2603 20 days ago

When using in vibe or opencode, often responds with just "Task completed" instead of actually doing the task

🚀 1

3

#16 opened 23 days ago by

sdroege

New activity in AesSedai/Mistral-Small-4-119B-2603-GGUF 21 days ago

Mistral-Small-4-119B-2603-Q5_K_M on 8 RTX 3090 with ik_llama.cpp ( compil 21 march 2026 )

❤️🔥 3

7

#1 opened 22 days ago by

martossien