Article
Introducing Cohere-transcribe: state-of-the-art speech recognition
CohereLabs
• • 46martossien
martossien
AI & ML interests
IA / IT Retrogaming emulator / ULM Pilot
Recent Activity
upvoted an article about 1 month ago
Introducing Cohere-transcribe: state-of-the-art speech recognition reacted to danielhanchen's post with 🔥 about 1 month ago
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! 🚀
Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing
Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth liked a model about 1 month ago
turboderp/Qwen3.6-27B-DFlash-exl3Organizations
None yet
upvoted an article about 1 month ago
reacted to danielhanchen's post with 🔥 about 1 month ago
Post
7748
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! 🚀
Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing
Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth
Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing
Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth
liked a
model about 1 month ago
liked a
model 2 months ago
Testing IQ5_K
❤️ 1
10
#8 opened 2 months ago
by 
shewin
Testing smol-IQ4_K
8
#4 opened 3 months ago
by shewin
liked 2
models 2 months ago
liked a
model 3 months ago
AesSedai/Kimi-K2.5-GGUF using the Q4_X on 8 RTX 3090
🚀 1
12
#7 opened 3 months ago
by martossien
liked a
model 3 months ago
liked 2
models 3 months ago
Mistral-Small-4-119B-2603-Q5_K_M on 8 RTX 3090 with ik_llama.cpp ( compil 21 march 2026 )
❤️🔥 3
7
#1 opened 3 months ago
by martossien
liked 2
models 3 months ago
liked a
model 4 months ago