🏝️ On Vacation

Ivan Fioravanti PRO

ivanfioravanti

·

AI & ML interests

None yet

Recent Activity

liked a model about 11 hours ago

JANGQ-AI/Qwen3.8-Flash-Next-JANGH4

liked a model 2 days ago

antirez/qwen3.8-flash-next-gguf

liked a model 4 days ago

TensorFold/Qwen3.8-Flash-Next-MLX-oQ4-MTP

View all activity

Organizations

New activity in ivanfioravanti/Qwen3.8-Flash-Next-DS4-IQ2 24 days ago

Confirmed on Mac Studio M4 Max 64GB — 38.7 t/s @ 32K, 38.9 t/s @ 64K, zero swap-ins

#2 opened 30 days ago by

New activity in ivanfioravanti/Qwen3.8-Flash-Next-DS4-IQ2 26 days ago

Confirmed on a 64GB M5 Pro: 128K OpenCode Coding-Agent Run

#4 opened 28 days ago by

New activity in ivanfioravanti/Qwen3.8-Flash-Next-DS4-Q4 28 days ago

Getting tool call error with DS4 - Qwen3.8-Flash-Next-DS4-Q4

#1 opened about 1 month ago by

New activity in ivanfioravanti/Qwen3.8-Flash-Next-DS4-IQ2 28 days ago

Benchmark report: Qwen3.8 Flash Next IQ2 on MacBook Pro M5 Pro 64GB

#3 opened 29 days ago by

New activity in ivanfioravanti/Qwen3.8-Flash-Next-DS4-IQ2 29 days ago

Qwen3.8-Flash-Next DS4 IQ2 — 64 GB Mac report (M1 Max)

#1 opened 30 days ago by

New activity in ivanfioravanti/deepseek-v4-gguf 3 months ago

It's a good model!

#1 opened 3 months ago by

New activity in mlx-community/MiniMax-M3-4bit 3 months ago

Loading + batched generation on mlx_vlm (3 fixes)

#1 opened 4 months ago by

New activity in 0xdfi/Qwen3.5-35B-A3B-REAP-pile10k-15p-MLX-q8 7 months ago

It works like a charm!

#1 opened 7 months ago by

New activity in Nanbeige/Nanbeige4.1-3B 8 months ago

License?

#5 opened 8 months ago by

New activity in Marvis-AI/marvis-tts-250m-v0.2 11 months ago

Update README.md

#1 opened 11 months ago by

New activity in ServiceNow-AI/Apriel-1.5-15b-Thinker about 1 year ago

Best Small model out there Butt....

#4 opened about 1 year ago by

New activity in mlx-community/Qwen3-235B-A22B-Instruct-2507-4bit-DWQ about 1 year ago

Remove_8bit_dwq

#3 opened about 1 year ago by

Wrong naming. Not DWQ, nor 4bit, but a regular 8 bit quant.

#1 opened about 1 year ago by

New activity in mlx-community/DeepSeek-R1-0528-4bit about 1 year ago

Is there a chance to get the AWQ or DWQ model? Mac Studio (512GB) has a 3-bit honey point.

#1 opened over 1 year ago by

New activity in mlx-community/DeepSeek-R1-0528-5bit over 1 year ago

Model fixed on 1st July

#1 opened over 1 year ago by

New activity in google/gemma-3-27b-it-qat-q4_0-gguf over 1 year ago

Ollama run returns authentication error on in Windows.

#3 opened over 1 year ago by

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 over 1 year ago

HF Format?

#2 opened over 1 year ago by

New activity in ivanfioravanti/Qwen2.5-3B-italian-wine-fp16 over 1 year ago

Upload folder using huggingface_hub

#1 opened over 1 year ago by

New activity in ivanfioravanti/Qwen2.5-3B-Instruct-italian-wine-fp16 over 1 year ago

Upload folder using huggingface_hub

#5 opened over 1 year ago by

Upload folder using huggingface_hub

#4 opened over 1 year ago by