Quantization publisher
Mindrend
Mindrend publishes 8 quantizations across 1 models in our index, averaging 5.168 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 8 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
8
Models covered
1
Avg effective bpw
5.168
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Mindrend | vs | Theirs | Difference |
|---|---|---|---|---|---|
| dolphin-2.7-mixtral-8x7b | Q2_K | 14.57 GiB | second-state | 14.57 GiB | 0.0% |
| dolphin-2.7-mixtral-8x7b | Q3_K_M | 18.96 GiB | second-state | 18.96 GiB | 0.0% |
| dolphin-2.7-mixtral-8x7b | Q4_0 | 24.63 GiB | second-state | 24.63 GiB | 0.0% |
| dolphin-2.7-mixtral-8x7b | Q4_K_M | 24.63 GiB | second-state | 24.63 GiB | 0.0% |
| dolphin-2.7-mixtral-8x7b | Q5_0 | 30.02 GiB | second-state | 30.02 GiB | 0.0% |
| dolphin-2.7-mixtral-8x7b | Q5_K_M | 30.02 GiB | second-state | 30.02 GiB | 0.0% |
| dolphin-2.7-mixtral-8x7b | Q6_K | 35.74 GiB | second-state | 35.74 GiB | 0.0% |
| dolphin-2.7-mixtral-8x7b | Q8_0 | 46.22 GiB | second-state | 46.22 GiB | 0.0% |
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 |
|---|---|---|
| dolphin-2.7-mixtral-8x7b | 8 | 14.57 GiB |