Firworks's picture

Firworks

Firworks

·

firworksyt

AI & ML interests

Local Inference, Fine Tunes, & NVFP4 Quantization

Recent Activity

liked a model about 7 hours ago

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

liked a model 3 days ago

kyutai/moshiko-pytorch-bf16

liked a model 3 days ago

nvidia/personaplex-7b-v1

View all activity

Organizations

None yet

New activity in Firworks/NVIDIA-Nemotron-3-Nano-30B-A3B-nvfp4 10 days ago

"NotImplementedError: is_act_and_mul=False" Error

#1 opened about 1 month ago by

New activity in Firworks/IQuest-Coder-V1-40B-Instruct-nvfp4 11 days ago

Loop instruct version?

#3 opened 11 days ago by

pathosethoslogos

New activity in Firworks/IQuest-Coder-V1-40B-Instruct-nvfp4 15 days ago

A little confused about model card

#2 opened 16 days ago by

pathosethoslogos

New activity in mradermacher/model_requests 18 days ago

Firworks/Qwen2.5-3B-Instruct-Reticent

#1675 opened 18 days ago by

New activity in Firworks/MiniMax-M2.1-nvfp4 22 days ago

Model request

#1 opened 23 days ago by

pathosethoslogos

New activity in Firworks/MiniMax-M2.1-nvfp4 23 days ago

how to run the model on vllm

#2 opened 23 days ago by

New activity in Firworks/Llama-3.3-70B-Joyous-nvfp4 24 days ago

nvFP4 script

#1 opened 24 days ago by

New activity in MiniMaxAI/MiniMax-M2.1 27 days ago

NVFP4?

#2 opened 29 days ago by

New activity in Firworks/Qwen3-Coder-REAP-25B-A3B-nvfp4 27 days ago

It works!

#1 opened 28 days ago by

New activity in Firworks/Qwen3-VL-32B-Thinking-nvfp4 27 days ago

Fix trailing comma in config.json

#2 opened 27 days ago by

New activity in cerebras/Qwen3-Coder-REAP-25B-A3B 29 days ago

NVFP4?

#9 opened 30 days ago by

New activity in Firworks/Ministral-3-14B-Instruct-2512-nvfp4 about 1 month ago

Issues while running the model within vLLMs nightly docker build as given in the readme

#1 opened about 1 month ago by

New activity in zai-org/GLM-4.6V-Flash about 1 month ago

vLLM error

#8 opened about 2 months ago by

New activity in Firworks/Cydonia-24B-v4.3-nvfp4 about 1 month ago

Need more info about your quant

#1 opened about 1 month ago by

New activity in google/gemma-3-270m-it about 1 month ago

Delete config.json

#14 opened about 1 month ago by

Delete model.safetensors

#13 opened about 1 month ago by

New activity in Firworks/INTELLECT-3-nvfp4 about 1 month ago

does not appear to have a file named configuration_glm4_moe.py

#7 opened about 1 month ago by

New activity in cerebras/MiniMax-M2-REAP-139B-A10B about 1 month ago

NVFP4 version

#2 opened about 1 month ago by

New activity in Firworks/KAT-Dev-72B-Exp-nvfp4 about 1 month ago

What tok/sec do you get on a PRO 6000 Blackwell?

#3 opened about 1 month ago by

New activity in Firworks/Devstral-Small-2-24B-Instruct-2512-nvfp4 about 1 month ago

What problem are you having? I might be able to help.

#2 opened about 1 month ago by