Gonzales's picture

Gonzales

Fernanda24

·

AI & ML interests

None yet

Recent Activity

new activity about 2 hours ago

eousphoros/DeepSeek-V3.2-NVFP4:Is it possible to make smaller NVFP4 quant at 340-360GB to fit in 4x96gb?

new activity about 2 hours ago

QuantTrio/DeepSeek-V3.2-AWQ:Aww Man!

new activity 1 day ago

Intel/DeepSeek-V3.1-Terminus-int4-mixed-AutoRound:Question will it work in vllm or sglang with rtx 6000 blackwells? cuda arch sm120

View all activity

Organizations

None yet

New activity in eousphoros/DeepSeek-V3.2-NVFP4 about 2 hours ago

Is it possible to make smaller NVFP4 quant at 340-360GB to fit in 4x96gb?

#1 opened 4 days ago by

New activity in QuantTrio/DeepSeek-V3.2-AWQ about 2 hours ago

Aww Man!

#1 opened 4 days ago by

New activity in Intel/DeepSeek-V3.1-Terminus-int4-mixed-AutoRound 1 day ago

Question will it work in vllm or sglang with rtx 6000 blackwells? cuda arch sm120

#1 opened about 2 months ago by

New activity in QuantTrio/DeepSeek-V3.1-AWQ-Lite 1 day ago

ooof this fits in 4x96gb can we get this for the new 3.2 Speciale ase well please :)

#2 opened 5 days ago by

New activity in tencent/DeepSeek-V3.1-Terminus-W4AFP8 2 days ago

4 x RTX PRO 6000

#1 opened 6 days ago by

New activity in eousphoros/DeepSeek-V3.2-NVFP4 2 days ago

How did you bypass deepseek-v32 not recognized in Tranformers?

#3 opened 3 days ago by

New activity in deepseek-ai/DeepSeek-V3.2 3 days ago

model type `deepseek_v32` not found

#16 opened 5 days ago by

New activity in mistralai/Ministral-3-14B-Instruct-2512 4 days ago

Update README.md

#4 opened 4 days ago by

broken link to mistral small

#3 opened 4 days ago by

New activity in apple/starflow 5 days ago

Cool!

#6 opened 5 days ago by

New activity in unsloth/DeepSeek-V3.2-Speciale 5 days ago

Thanks!

#1 opened 5 days ago by

New activity in Intel/DeepSeek-V3.1-Terminus-int4-mixed-AutoRound 5 days ago

can we get this for the new Deepseek v3.2?

#2 opened 5 days ago by

New activity in lukealonso/MiniMax-M2-NVFP4 5 days ago

you know which nightly it worked with? because it does not with current one

#1 opened 24 days ago by

New activity in Firworks/INTELLECT-3-nvfp4 5 days ago

is NVFP4 supported on sm120 (blackwell rtx pro 6000, rtx 5090 etc)?

#4 opened 6 days ago by

New activity in cerebras/Kimi-Linear-REAP-35B-A3B-Instruct 6 days ago

Kimi K2 Thinking REAP?

#6 opened 6 days ago by

New activity in bartowski/MiniMaxAI_MiniMax-M2-GGUF 7 days ago

best quant avail but maybe needs new jinja template?

#1 opened 7 days ago by

New activity in PrimeIntellect/INTELLECT-3 7 days ago

sampling params temp etc.?

#6 opened 7 days ago by

ubergarm ik_llama.cpp quant

#5 opened 7 days ago by

Update chat_template.jinja

#2 opened 9 days ago by

latent-variable

New activity in bartowski/PrimeIntellect_INTELLECT-3-GGUF 7 days ago

first

#1 opened 7 days ago by