Banibrata Dutta

bdutta

·

bdutta

AI & ML interests

None yet

Organizations

New activity in prism-ml/Ternary-Bonsai-27B-gguf 2 months ago

Beware of the kv_cache params!

#36 opened 2 months ago by

MOE or changing to A3B

#43 opened 2 months ago by

Tom-Neverwinter

New activity in prism-ml/Ternary-Bonsai-27B-mlx-2bit 2 months ago

What and when to expect better long-horizon, multi-file agentic coding support (and more...)

#4 opened 2 months ago by

New activity in yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF 3 months ago

Has anyone compared this model against OmniCoder-9B on real life coding or things like Aider benchmarks ?

#30 opened 3 months ago by

C# & Java

#27 opened 3 months ago by

QAT and/or Q3 version

#21 opened 3 months ago by

New activity in lemuralabs/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-abliterated-OptiQ-3.7bpw-mlx 4 months ago

Anyone tried this with oMLX ?

#1 opened 4 months ago by

New activity in LiquidAI/LFM2-24B-A2B 7 months ago

No other benchmarks than prefill speed and token generation speed ?

#3 opened 7 months ago by

New activity in mlx-community/README 11 months ago

Is "jedisct1/Qwen3-Coder-30B-A3B-Instruct-q4-mlx" a valid/good conversion of Unsloth's dyn 4bit quant of Qwen3 30B Coder ?

#25 opened 11 months ago by

New activity in google/gemma-3n-E4B-it about 1 year ago

This model is amazing, but almost too amazing

#16 opened about 1 year ago by

New activity in google/gemma-3n-E4B-it-litert-preview over 1 year ago

Would there ever be a GGUF for the gemma-3n models ?

#11 opened over 1 year ago by

New activity in mlx-community/gemma-3-12b-it-4bit over 1 year ago

LM-studio error

#1 opened over 1 year ago by

Broken model?

#4 opened over 1 year ago by

Broken model?

#4 opened over 1 year ago by