Christian Otto Stelter's picture

28 1 8

Christian Otto Stelter PRO

stelterlab

·

stelterlab

AI & ML interests

None yet

Recent Activity

new activity about 2 months ago

mistralai/Ministral-3-14B-Instruct-2512:NVFP4 / AWQ Quants or llm-compressor recipe

new activity 2 months ago

cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit:vLLM v0.11.1 seems to work, but v0.11.2 fails

new activity 5 months ago

cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit:Error when running in VLLM

View all activity

Organizations

None yet

New activity in mistralai/Ministral-3-14B-Instruct-2512 about 2 months ago

NVFP4 / AWQ Quants or llm-compressor recipe

#1 opened about 2 months ago by

New activity in cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit 2 months ago

vLLM v0.11.1 seems to work, but v0.11.2 fails

#3 opened 2 months ago by

New activity in cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit 5 months ago

Error when running in VLLM

#1 opened 5 months ago by

New activity in stelterlab/Qwen3-Coder-30B-A3B-Instruct-AWQ 6 months ago

Unable to run the model in VLLM: KeyError: 'layers.14.mlp.gate.qweight'

#1 opened 6 months ago by

fredericodeveloper

New activity in stelterlab/DeepSeek-R1-0528-Qwen3-8B-AWQ 6 months ago

Rope Scaling pre-applied?

#1 opened 7 months ago by

New activity in mistralai/Mistral-Small-3.2-24B-Instruct-2506 6 months ago

AWQ version

#8 opened 7 months ago by

New activity in OPEA/Mistral-Small-3.1-24B-Instruct-2503-int4-AutoRound-awq-sym 7 months ago

How did you use auto-round to quantize?

#4 opened 7 months ago by

New activity in stelterlab/Mistral-Small-24B-Instruct-2501-AWQ 7 months ago

please update to Mistral-Small-3.2-24B-Instruct-2506

#5 opened 7 months ago by

New activity in stelterlab/Mistral-Small-24B-Instruct-2501-AWQ 8 months ago

Tool Calling issue with stelterlab/Mistral-Small-24B-Instruct-2501-AWQ

#4 opened 9 months ago by

New activity in stelterlab/Qwen3-32B-AWQ 9 months ago

Do you any plan to quantize the Qwen3-30B-A3B-AWQ model?

#2 opened 9 months ago by

New activity in stelterlab/Qwen3-8B-AWQ 9 months ago

Could you share the code script that convert the original Qwen3-8B to Qwen3-8B-AWQ?

#1 opened 9 months ago by

New activity in stelterlab/Qwen3-32B-AWQ 9 months ago

gpqa diamond

#1 opened 9 months ago by

New activity in stelterlab/DeepSeek-R1-Distill-Qwen-14B-AWQ 9 months ago

How to reduce "Think" responses when using vLLM for inference?

#1 opened 9 months ago by

New activity in stelterlab/Mistral-Small-24B-Instruct-2501-AWQ 9 months ago

Really good work

#1 opened 12 months ago by

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 10 months ago

FP8 Dynamic/W8A16 Quants Please

#44 opened 10 months ago by

New activity in stelterlab/openhands-lm-32b-v0.1-AWQ 10 months ago

i love you

#1 opened 10 months ago by

New activity in stelterlab/Mistral-Small-24B-Instruct-2501-AWQ 10 months ago

Upload tekken.json

#3 opened 10 months ago by

Upload params.json

#2 opened 10 months ago by

tuong-nguyen-prd

New activity in open-r1/OlympicCoder-32B 11 months ago

AWQ versions

#1 opened 11 months ago by

New activity in stelterlab/EuroLLM-9B-Instruct-MLX-4bit about 1 year ago

Upload folder using huggingface_hub

#1 opened about 1 year ago by