Every post of theirs in the library
Loading their posts
Awni Hannun
Writes about AI. 64% of posts open with an observation. A typical post reaches 687 likes.
- Posts
- 11
- Likes
- 11K
- Typical
- 687
- Best
- 2.9K
What they write about
How they open
Every post of theirs in the library
| Post | Topic | Likes | Replies | Reposts | Score | Posted | Actions |
|---|---|---|---|---|---|---|---|
| @awnihannunThe new 1 Trillion parameter Kimi K2 Thinking model runs well on 2 M3 Ultras in its native… | AI | 2.9K | 76 | — | 54 | ||
| @awnihannunKimi K2.5 1T runs on 2 M3 Ultras with mlx-lm in it's native precision. It's actually quite… | AI | 2K | 75 | — | 51 | ||
| @awnihannunWow, DeepSeek R1 Distill Qwen 7B (in 4-bit) nailed the first hard math question I asked it… | AI | 1.6K | 38 | — | 45 | ||
| @awnihannunQwQ-32B evals on par with Deep Seek R1 680B but runs fast on a laptop. Delivery accepted. … | AI | 1.1K | 36 | — | 42 | ||
| @awnihannunGLM-4.7 runs quite well on an M3 Ultra with mlx-lm, even at a near lossless precision (6-b… | AI | 874 | 28 | — | 44 | ||
| @awnihannunNemotron 3 Nano runs nicely with mlx-lm on an M4 Max. Could be a great model for local use… | AI | 687 | 14 | — | 41 | ||
| @awnihannunM5 Max is faster than M3 Ultra for many MLX benchmarks (prefill 2x, decode for MoEs despit… | AI | 633 | 23 | — | 41 | ||
| @awnihannunI'm a bit giddy over the fact that this is by all visible measures a frontier level model,… | AI | 503 | 27 | — | 39 | ||
| @awnihannunM5 Max is a local AI powerhouse in a laptop form factor. So awesome to see this thing rele… | AI | 482 | 31 | — | 39 | ||
| @awnihannunNew Mixtral 8x22B runs nicely in MLX on an M2 Ultra. 4-bit quantized model in the 🤗 MLX C… | AI | 377 | 14 | — | 34 | ||
| @awnihannunQwen3.5 runs quite well in mlx-lm. Awesome that we have a frontier-level hybrid model. The… | AI | 241 | 15 | — | 33 |