Laxmi Kant

laxmimerit's activity

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

New activity in Qwen/Qwen-Image-2.1 2 days ago

Qwen-Image-2.1: Quantized Inference Measurements on a Single RTX 5090

❤️🚀 1

#32 opened 2 days ago by

laxmimerit

New activity in zai-org/GLM-5.3-Flash 8 days ago

Reading GLM 5.3 Flash from config.json: 6.0 KB of KV Cache per Token

#55 opened 8 days ago by

laxmimerit

New activity in deepseek-ai/DeepSeek-V4.1-Flash 13 days ago

Reading DeepSeek V4.1 Flash's config.json: Where Sparse Attention Lives

🚀❤️ 1

#38 opened 13 days ago by

laxmimerit

New activity in ornith-ai/Ornith-1.5-35B-A3B 27 days ago

I Benchmarked on RTX 5090: 271 tok/s generation, 673 tok/s at 8 concurrent, 32 KB/token KV cache

2

#31 opened 27 days ago by

laxmimerit

New activity in Qwen/Qwen3.8-Flash-Next 28 days ago

Run Qwen 3.8 Flash Next (Qwen 4) 180B on CPU Only, No GPU Needed

🔥❤️ 9

3

#29 opened 28 days ago by

laxmimerit

Qwen3.8-Flash-Next (Qwen 4 - Preview) vs 3.8 27B - Architecture Teardown

🔥❤️ 8

6

#22 opened 29 days ago by

laxmimerit

New activity in Qwen/Qwen3.8-27B about 1 month ago

Benchmarked Qwen3.8-27B vs Nemotron 3.5 Lightning and Muse Glimmer on 16 hard problems (RTX 5090, Q4_K_M)

🔥❤️ 11

13

#103 opened about 1 month ago by

laxmimerit

This model cannot stop thinking

🧠➕ 9

5

#113 opened about 1 month ago by

xvcy3w

Follow-up: I benchmarked 45 llama.cpp settings on Qwen3.8-27B. The MTP draft head is worth 1.81x, free (RTX 5090, Q4_K_M)

🚀❤️ 9

2

#112 opened about 1 month ago by

laxmimerit

Benchmarked Qwen3.8-27B vs Nemotron 3.5 Lightning and Muse Glimmer on 16 hard problems (RTX 5090, Q4_K_M)

🔥❤️ 11

13

#103 opened about 1 month ago by

laxmimerit

Benchmarked Qwen3.8-27B vs Nemotron 3.5 Lightning and Muse Glimmer on 16 hard problems (RTX 5090, Q4_K_M)

🔥❤️ 11

13

#103 opened about 1 month ago by

laxmimerit