Man Cub

mancub's activity

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

New activity in Minachist/Qwen3.6-35B-A3B-INT8-AutoRound about 16 hours ago

Crashes with newest vllm version (v0.20.1)

14

#1 opened 9 days ago by

Neiko2002

New activity in froggeric/Qwen-Fixed-Chat-Templates 1 day ago

v13 stops dead after the first response

👍 2

2

#14 opened 1 day ago by

mancub

New activity in froggeric/Qwen-Fixed-Chat-Templates 3 days ago

v11/v12 performance considerations with Claude Code?

3

#11 opened 3 days ago by

mancub

When using Claude Code, tool calls end up broken with this chat template in Qwen3.6-27B

6

#6 opened 5 days ago by

mancub

New activity in z-lab/Qwen3.6-27B-DFlash 6 days ago

RuntimeError: expected mat1 and mat2 to have the same dtype, but got: float != c10::Half

#10 opened 6 days ago by

mancub

New activity in Minachist/Qwen3.6-27B-INT8-AutoRound 7 days ago

Good quant!

12

#1 opened 11 days ago by

qenme

New activity in Intel/gemma-4-31B-it-int4-AutoRound 7 days ago

INT8 version for TP=2 / dual Ampere GPUs?

🚀 1

#6 opened 7 days ago by

mancub

New activity in QuantTrio/gemma-4-31B-it-AWQ 8 days ago

Does not appear to work with the new google drafter MTP model

#2 opened 8 days ago by

mancub

New activity in google/gemma-4-31B-it-assistant 8 days ago

Is it supposed to work in vllm?

1

#2 opened 8 days ago by

mancub

New activity in z-lab/Qwen3.6-27B-DFlash 16 days ago

Avg Draft acceptance rate is low.

17

#2 opened 19 days ago by

fouvy

New activity in LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF 21 days ago

OOM and context limits reached too soon

1

#5 opened 22 days ago by

mancub

New activity in rdtand/Qwen3.6-27B-PrismaQuant-5.5bit-vllm 21 days ago

Unable to run on 3090

1

#1 opened 21 days ago by

mancub

New activity in AesSedai/Qwen3.6-35B-A3B-GGUF 21 days ago

Q6_K?

9

#1 opened 27 days ago by

qenme

New activity in ubergarm/Qwen3.5-122B-A10B-GGUF 21 days ago

How to split this model between 2 (3) GPUs and CPU/RAM ?

30

#12 opened about 2 months ago by

mancub

New activity in QuantTrio/Qwen3.5-27B-AWQ about 1 month ago

My personal vLLM launch cmd on my old personal 2x3090 workstation

7

#1 opened 2 months ago by

tclf90

New activity in mudler/gemma-4-26B-A4B-it-APEX-GGUF about 1 month ago

What was just updated and why?

👍 1

2

#1 opened about 1 month ago by

mancub

New activity in adamjen/Devstral-Small-2-24B-Opus-Reasoning about 2 months ago

How to use it with llama-server ?

👀 1

3

#1 opened about 2 months ago by

mancub

New activity in noctrex/Mistral-Small-4-119B-2603-MXFP4_MOE-GGUF about 2 months ago

Poor performance and pretty lobotomized

2

#1 opened about 2 months ago by

mancub

New activity in mistralai/Mistral-Small-4-119B-2603 about 2 months ago

Love the license, confused by some of the decisions.

🤝👍 16

15

#15 opened about 2 months ago by

CyborgPaloma

New activity in noctrex/Qwen3.5-35B-A3B-MXFP4_MOE-GGUF 2 months ago

It's really good.

👀 1

26

#3 opened 3 months ago by

Shuasimodo