Tom

TomLucidor's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in bknyaz/Qwen3-Next-80B-A3B-Instruct-REAM about 16 hours ago

Has REAM been checked for their resilience towards quantization?

4

#1 opened 30 days ago by

TomLucidor

New activity in nightmedia/Qwen3.5-35B-A3B-Text-qx64-hi-mlx 2 days ago

How is this different from the other quants?

8

#1 opened 4 days ago by

TomLucidor

New activity in TheDrummer/Cydonia-24B-v4.3 3 days ago

Will Hybrid Attention RP models get some love?

➕ 1

#7 opened 3 days ago by

TomLucidor

New activity in mlx-community/LFM2-8B-A1B-4bit 6 days ago

ValueError: Model type lfm2_moe not supported.

5

#1 opened 5 months ago by

kadirnar

New activity in mlx-community/LFM2-8B-A1B-8bit-MLX 6 days ago

Runs Amazing on M4 Macbook air!

1

#1 opened 4 months ago by

leo253

New activity in bknyaz/Qwen3-Coder-Next-REAM 8 days ago

Could more benchmarks be done on Instruction Following / Function Calling?

4

#2 opened 17 days ago by

TomLucidor

New activity in lmsys/SGLang-EAGLE3-Qwen3-Next-80B-A3B-Instruct-FP8-SpecForge-Meituan 9 days ago

The comparison with the original MTP

👍 1

1

#2 opened 11 days ago by

Michalea

New activity in deepgenteam/DeepGen-1.0 10 days ago

Using ZwZ and better VLM along side DeepGen

4

#6 opened 14 days ago by

TomLucidor

New activity in AngelSlim/Qwen3-a3B_eagle3 13 days ago

Could you make an Eagle3 model for Nemotron-3-Nano?

#4 opened 13 days ago by

TomLucidor

New activity in allenai/SERA-32B-GA 13 days ago

Guys please make 30b a3b like MOE model

👍 1

1

#2 opened 28 days ago by

Narutoouz

New activity in LiquidAI/LFM2-8B-A1B 13 days ago

Can this be scaled into Claude Code / OpenCode / Codex?

#9 opened 13 days ago by

TomLucidor

New activity in inclusionAI/Ring-2.5-1T 13 days ago

WIll there be a "Ring Flash" or "RIng-Mini" for V2.5?

🤝 😔 2

#6 opened 13 days ago by

TomLucidor

New activity in bknyaz/Qwen3-Coder-Next-REAM 14 days ago

Please add quality Q6/Q4/Q3 quants to this

7

#1 opened 17 days ago by

TomLucidor

New activity in huang3eng/SGLang-EAGLE3-Qwen3-Next-80B-A3B-Instruct-SpecForge 14 days ago

Q: could this work with the REAM models?

#2 opened 14 days ago by

TomLucidor

Q: How is this different from the other Eagle3?

#1 opened 14 days ago by

TomLucidor

New activity in bknyaz/Qwen3-Coder-Next-REAM 14 days ago

New issue: naive REAM not supporting MTP?

1

#5 opened 14 days ago by

TomLucidor

New activity in deepgenteam/DeepGen-1.0 14 days ago

Comparison to Emu

1

#5 opened 14 days ago by

TomLucidor

New activity in RichardErkhov/google_-_recurrentgemma-2b-it-4bits 14 days ago

Request for <4B linear attention quants

4

#1 opened 15 days ago by

TomLucidor

New activity in ai21labs/AI21-Jamba2-Mini-FP8 15 days ago

Q4-like quant for accelerated compute?

#2 opened 15 days ago by

TomLucidor

New activity in lkevincc0/Step-3.5-Flash-REAP-128B-A11B 15 days ago

REAMing Step-3.5 instead of REAPing

👍 2

2

#1 opened 17 days ago by

TomLucidor