Man Cub

mancub's activity

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

liked a model 2 days ago

peasantsmith/GLM-5.3-Flash-Maya-GGUF

Text Generation • Updated 3 days ago • 71.7k • 32

New activity in Minachist/Muse-Glimmer-30B-INT8-AutoRound 23 days ago

So what do you think of it so far?

14

#1 opened 2 months ago by

mancub

liked a dataset about 2 months ago

malcolmrey/various

Viewer • Updated 7 days ago • 33 • 39.8k • 284

New activity in Hikari07jp/gemma4-repe-uncensor 3 months ago

Why not just patch the model?

👍 1

6

#1 opened 3 months ago by

mancub

New activity in llmfan46/gemma-4-31B-it-qat-q4_0-uncensored-heretic-GPTQ-Int4 4 months ago

Does not load into vllm- layer 5 fusion issue

2

#1 opened 4 months ago by

mancub

New activity in cyankiwi/gemma-4-12B-it-qat-AWQ-INT4 4 months ago

Vllm and SgLang command please

👍 1

5

#1 opened 4 months ago by

mtcl

New activity in OBLITERATUS/Gemma-4-12B-OBLITERATED 4 months ago

Does this jaibreak version suppor mtp?

1

#1 opened 4 months ago by

victor11sk

New activity in z-lab/Qwen3.6-27B-DFlash 5 months ago

Are we going to see an update to this model?

👀 7

#15 opened 5 months ago by

mancub

New activity in Intel/gemma-4-31B-it-int4-AutoRound 5 months ago

INT8 version for TP=2 / dual Ampere GPUs?

🚀 1

1

#6 opened 5 months ago by

mancub

New activity in z-lab/Qwen3.6-27B-DFlash 5 months ago

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

3

#10 opened 5 months ago by

mancub

New activity in AesSedai/Qwen3.6-35B-A3B-GGUF 5 months ago

Q6_K?

15

#1 opened 6 months ago by

qenme

New activity in froggeric/Qwen-Fixed-Chat-Templates 5 months ago

final v16 does not appear to work correctly, it stops after the first prompt.

🔥 2

2

#19 opened 5 months ago by

mancub

v13 stops dead after the first response

👍 2

5

#14 opened 5 months ago by

mancub

New activity in Minachist/Qwen3.6-35B-A3B-INT8-AutoRound 5 months ago

Crashes with newest vllm version (v0.20.1)

15

#1 opened 5 months ago by

Neiko2002

New activity in froggeric/Qwen-Fixed-Chat-Templates 5 months ago

v11/v12 performance considerations with Claude Code?

3

#11 opened 5 months ago by

mancub

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

7

#6 opened 5 months ago by

mancub

New activity in Minachist/Qwen3.6-27B-INT8-AutoRound 5 months ago

Good quant!

12

#1 opened 5 months ago by

qenme

New activity in QuantTrio/gemma-4-31B-it-AWQ 5 months ago

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

#2 opened 5 months ago by

mancub

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

Is it supposed to work in vllm?

1

#2 opened 5 months ago by

mancub

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

Avg Draft acceptance rate is low.

17

#2 opened 6 months ago by

fouvy