Instructions to use amgadtewfik/atf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use amgadtewfik/atf with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download amgadtewfik/atf --local-dir atf
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -42,6 +42,7 @@ formats are now bandwidth-bound, not kernel-bound, on Apple hardware.
|
|
| 42 |
| `Qwen3.5-9B-IQ4_NL.atf` | 5.5 GB | IQ4_NL + Q6_K lm_head | **12.96 tok/s** | 2.3 s warm / 9.6 s cold |
|
| 43 |
| `Qwen3.5-9B-mlx4bit.atf` | 6.9 GB | MLX 4-bit | ~12–13 tok/s | seconds |
|
| 44 |
| `Qwen3.8-27B-UD-Q2_K_XL.atf` | 9.5 GB | UD-Q2_K_XL (mixed K/IQ) | **4.73 tok/s** | ~15 s |
|
|
|
|
| 45 |
|
| 46 |
*Benchmarks: Apple M4, 16 GB unified memory, greedy decode, 4k context, warm
|
| 47 |
pass. All three run comfortably on a 16 GB Mac.*
|
|
|
|
| 42 |
| `Qwen3.5-9B-IQ4_NL.atf` | 5.5 GB | IQ4_NL + Q6_K lm_head | **12.96 tok/s** | 2.3 s warm / 9.6 s cold |
|
| 43 |
| `Qwen3.5-9B-mlx4bit.atf` | 6.9 GB | MLX 4-bit | ~12–13 tok/s | seconds |
|
| 44 |
| `Qwen3.8-27B-UD-Q2_K_XL.atf` | 9.5 GB | UD-Q2_K_XL (mixed K/IQ) | **4.73 tok/s** | ~15 s |
|
| 45 |
+
| `Qwen-AgentWorld-35B-A3B-UD-IQ2_M.atf` | 11.64 GB | **IQ2_M (unsloth dynamic)** | **6.5 tok/s** | ~20 s |
|
| 46 |
|
| 47 |
*Benchmarks: Apple M4, 16 GB unified memory, greedy decode, 4k context, warm
|
| 48 |
pass. All three run comfortably on a 16 GB Mac.*
|