Victor C.

dehnhaide's activity

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

New activity in AesSedai/Mistral-Small-4-119B-2603-GGUF about 21 hours 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 2 days ago by

martossien

New activity in mistralai/Mistral-Small-4-119B-2603 about 21 hours ago

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

🚀 1

1

#16 opened 2 days ago by

sdroege

New activity in unsloth/Mistral-Small-4-119B-2603-GGUF 1 day ago

which template for opencode toolcalling?

🚀 1

1

#7 opened 1 day ago by

dfsafdsf

New activity in NeuroSenko/Qwen3.5-397B-A17B-exl3 1 day ago

Tool calling

5

#1 opened 2 days ago by

dehnhaide

New activity in ubergarm/MiniMax-M2.5-GGUF 3 days ago

ik_llama.cpp version

12

#11 opened about 1 month ago by

geveent

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

The RX3090 works very well，ths！

❤️👍 3

1

#2 opened 6 days ago by

summerbuild

New activity in Intel/Step-3.5-Flash-int4-mixed-AutoRound 3 days ago

Work great on 3090 except for weird (...) generation

❤️ 1

4

#1 opened 11 days ago by

ortegaalfredo

New activity in ubergarm/MiniMax-M2.5-GGUF 7 days ago

8x RTX 3090, EPYC 7532, 512GB RAM: Benchmarking MiniMax-M2.5-IQ4_NL for High-Speed Coding (35-75 t/s) with opencode

🔥 2

12

#10 opened about 1 month ago by

martossien

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 11 days ago

accuracy

23

#4 opened about 1 month ago by

ktsaou

New activity in ubergarm/Step-3.5-Flash-GGUF 12 days ago

IQ5_K 136.891 GiB

🔥 2

30

#9 opened about 1 month ago by

Hunterx

New activity in ubergarm/MiniMax-M2.5-GGUF 16 days ago

Testing IQ4_NL

13

#12 opened about 1 month ago by

shewin

New activity in mratsim/MiniMax-M2.5-FP8-INT4-AWQ 16 days ago

tool hallucinations and bad tool calls

6

#1 opened 16 days ago by

jcowles

New activity in ubergarm/Qwen3.5-397B-A17B-GGUF 21 days ago

Request for support - improved model fit

9

#9 opened 26 days ago by

dehnhaide

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 23 days ago

How many GPUs for 8 or higher concurrency using RTX 3090s Rig ?

1

#9 opened 28 days ago by

BiggestFox

New activity in noctrex/Qwen3.5-122B-A10B-MXFP4_MOE-GGUF 24 days ago

Kind request for Qwen3.5-397B-A17B MXFP4 BF16

7

#2 opened 25 days ago by

dehnhaide

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 26 days ago

Testing IQ4_KSS

4

#5 opened 26 days ago by

shewin

New activity in mratsim/MiniMax-M2.5-BF16-INT4-AWQ 28 days ago

Cant get it to work on 8x RTX3090

14

#1 opened about 1 month ago by

maglat

New activity in EliasOenal/MiniMax-M2.5-Hybrid-AWQ-W4A16G128-Attn-fp8_e4m3-KV-fp8_e4m3 30 days ago

Crashes on 8x RTX 3090

3

#1 opened 30 days ago by

dehnhaide

New activity in lukealonso/MiniMax-M2.5-NVFP4 about 1 month ago

"w1_weight_scale_2 must match w3_weight_scale_2. Accuracy may be affected."

👍 1

21

#2 opened about 1 month ago by

zenmagnets

New activity in ubergarm/MiniMax-M2.5-GGUF about 1 month ago

Looking forward to IQ4_XS!

🔥 3

24

#1 opened about 1 month ago by

tarruda