Quantization publisher
mrfakename
mrfakename publishes 16 quantizations across 1 models in our index, averaging 5.829 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
1
Quantizations
16
Models covered
1
Avg effective bpw
5.829
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | mrfakename | vs | Theirs | Difference |
|---|---|---|---|---|---|
| mistral-small-3.1-24b-instruct-2503-hf | Q2_K | 8.28 GiB | MaziyarPanahi | 8.28 GiB | -0.0% |
| mistral-small-3.1-24b-instruct-2503-hf | Q3_K_L | 11.55 GiB | MaziyarPanahi | 11.55 GiB | -0.0% |
| mistral-small-3.1-24b-instruct-2503-hf | Q3_K_M | 10.69 GiB | MaziyarPanahi | 10.69 GiB | -0.0% |
| mistral-small-3.1-24b-instruct-2503-hf | Q3_K_S | 9.69 GiB | MaziyarPanahi | 9.69 GiB | -0.0% |
| mistral-small-3.1-24b-instruct-2503-hf | Q4_K_S | 12.62 GiB | MaziyarPanahi | 12.62 GiB | -0.0% |
| mistral-small-3.1-24b-instruct-2503-hf | Q5_K_M | 15.61 GiB | MaziyarPanahi | 15.61 GiB | -0.0% |
| mistral-small-3.1-24b-instruct-2503-hf | Q5_K_S | 15.18 GiB | MaziyarPanahi | 15.18 GiB | -0.0% |
| mistral-small-3.1-24b-instruct-2503-hf | Q6_K | 18.02 GiB | MaziyarPanahi | 18.02 GiB | -0.0% |
| mistral-small-3.1-24b-instruct-2503-hf | Q8_0 | 23.33 GiB | MaziyarPanahi | 23.33 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 |
|---|---|---|
| mistral-small-3.1-24b-instruct-2503-hf | 16 | 8.28 GiB |