Quantization publisher
lordx64
lordx64 publishes 14 quantizations across 4 models in our index, averaging 5.795 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 9 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
6
Quantizations
14
Models covered
4
Avg effective bpw
5.795
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | lordx64 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Qwable-v1 | Q8_0 | 34.37 GiB | bartowski | 35.22 GiB | -2.4% |
| Qwable-v2 | Q8_0 | 34.37 GiB | mradermacher | 35.21 GiB | -2.4% |
| Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled | Q8_0 | 34.37 GiB | huihui-ai | 35.21 GiB | -2.4% |
| Qwable-v1 | Q5_K_M | 23.03 GiB | bartowski | 23.74 GiB | -3.0% |
| Qwable-v1 | Q4_K_M | 19.71 GiB | bartowski | 20.36 GiB | -3.2% |
| Qwable-v2 | Q5_K_M | 23.03 GiB | mradermacher | 23.61 GiB | -2.4% |
| Qwable-v2 | Q4_K_M | 19.71 GiB | mradermacher | 20.22 GiB | -2.5% |
| Qwable-v2 | IQ4_XS | 17.64 GiB | mradermacher | 18.06 GiB | -2.3% |
| Qwable-v1 | IQ4_XS | 17.64 GiB | bartowski | 17.95 GiB | -1.8% |
A quantization label describes a target, not a recipe. Publishers make different choices about which tensors to keep at higher precision, and some apply an importance matrix while others don't — so two files both honestly labelled the same thing can differ measurably in size and in quality.
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled | 3 | 17.64 GiB |
| Qwable-v2 | 4 | 17.64 GiB |
| Qwable-v1 | 4 | 17.64 GiB |
| Qwen3.6-35B-A3B-Kimi-K2.6-Reasoning-Distilled | 3 | 17.64 GiB |