Quantization format
TQ2_0
TQ2_0 has a nominal rate of — bits per weight. We have no measured files carrying this label yet.
From the file· 19 files measured
Nominal bpw
—
from the block layout
Measured average
2.808
19 files
Range
2.069–4.495
varies by architecture
File sizes
0.02 GiB+
up to 8.82 GiB
Real files
one per model, most downloaded first
| Model | Size● | Effective bpw● | vs nominal● |
|---|---|---|---|
| Qwen-Image-Edit-2509 | 6.52 GiB | 2.739 | — |
| Qwen3-0.6B-Base | 0.31 GiB | 4.495 | — |
| Qwen-Image-Edit | 6.55 GiB | 2.753 | — |
| HopCoder-Mini-35B-A3B-VL36 | 8.82 GiB | 2.158 | — |
| Wan_2.2_ComfyUI_Repackaged | 1.52 GiB | — | — |
| gemma-4-26B-A4B | 8.71 GiB | 2.819 | — |
| Llama-3.2-3B | 0.99 GiB | 2.635 | — |
| diffusiongemma-26B-A4B-it-HERETIC-Uncensored | 8.72 GiB | 2.900 | — |
| Qwen3.5-9B-Base | 2.99 GiB | 2.656 | — |
| Qwen3.5-2B | 0.75 GiB | 2.814 | — |
| granite-3.1-8b-instruct | 2.07 GiB | 2.176 | — |
| Supra-Router-51M | 0.02 GiB | 4.077 | — |
| Maestro1-9B | 2.48 GiB | 2.426 | — |
| bitnet_b1_58-large | 0.20 GiB | 2.383 | — |
| BugTraceAI-Apex-G4-26B-Master-f16 | 8.71 GiB | 2.965 | — |
| Supra-50M-Base | 0.02 GiB | 4.077 | — |
| Ternary-Bonsai-8B-gguf | 1.97 GiB | 2.069 | — |
| granite-3.1-2b-instruct | 0.66 GiB | 2.249 | — |
| Ternary-Bonsai-8B | 2.25 GiB | 2.359 | — |
●From the filewhat these mean