Benjamin Marie PRO

bnjmnmarie's activity

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

New activity in kaitchup/Qwen3.8-27B-SLQ-GGUF 10 days ago

IQ4XS?

1

#2 opened 10 days ago by

shing3232

MTP

1

#1 opened 10 days ago by

bobbytaylor

New activity in kaitchup/Qwen3.8-27B-hum-quality-MTP-19.2GB 2 months ago

Maybe add vLLM FP8 KVCache calibration scales

4

#2 opened 2 months ago by

ibaldonl

New activity in kaitchup/Ornith-1.5-9B-hum-high 2 months ago

Mixed up model names

2

#1 opened 2 months ago by

owao

New activity in kaitchup/MiniMax-M3-GGUF-MoQ 4 months ago

Which llama.cpp version?

3

#2 opened 4 months ago by

MLDataScientist

New activity in kaitchup/Qwen3.6-27B-GGUF-MoQ 5 months ago

LMStudio sees the GGUF as MTP enabled

4

#2 opened 5 months ago by

Hachann

Higher-BPW MoQ variant (bf16 K/V + Q5_K FFN)?

🧠 1

2

#1 opened 5 months ago by

zockin

New activity in 0xSero/Qwen3.6-28B 6 months ago

error with vLLM

6

#3 opened 6 months ago by

bnjmnmarie

New activity in kaitchup/Qwen3.5-27B-autoround-NVFP4-linearattn-BF16 7 months ago

ValueError: Tokenizer class TokenizersBackend does not exist or is not currently imported

3

#1 opened 7 months ago by

Qnibbles

New activity in kaitchup/Olmo-3.1-32B-Instruct-fp8-dynamic 10 months ago

Error running vllm 12

1

#1 opened 10 months ago by

evetsagg

New activity in mistralai/Ministral-3-14B-Reasoning-2512 11 months ago

Reasoning not parsing correctly within VLLM

11

#4 opened 11 months ago by

SuperbEmphasis

New activity in Firworks/INTELLECT-3-nvfp4 11 months ago

works with vLLM, with FLASHINFER_MOE_FP4

1

#2 opened 11 months ago by

bnjmnmarie

New activity in kaitchup/Olmo-3-7B-Instruct-fp8-dynamic 12 months ago

Update README.md

#1 opened 12 months ago by

bmarie

New activity in microsoft/UserLM-8b about 1 year ago

Question about Llama 3.1 license compliance

😎👍 7

3

#3 opened about 1 year ago by

tokinasin

New activity in unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF over 1 year ago

qwen3moe instead of qwen3_moe?

3

#5 opened over 1 year ago by

bnjmnmarie

New activity in kaitchup-toolboxes/Qwen2.5 over 1 year ago

How can I get the access?

1

#1 opened over 1 year ago by

minjunsz

New activity in kaitchup/Qwen2.5-72B-Instruct-AutoRound-GPTQ-4bit over 1 year ago

how to run this model

4

#1 opened over 1 year ago by

cicdatopea

New activity in kaitchup/QwQ-32B-AutoRoundGPTQ-4bit over 1 year ago

Qwen-32B overflow issue

8

#1 opened over 1 year ago by

cicdatopea

New activity in kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit over 1 year ago

Your quants are not listed in the base model

2

#2 opened over 1 year ago by

dazipe

New activity in kaitchup/Mistral-Small-24B-Instruct-2501-AutoRound-GPTQ-4bit over 1 year ago

Any plan for 8 bit?

1

#1 opened over 1 year ago by

jm4n21