Quantization publisher
saidutta69
saidutta69 publishes 10 quantizations across 2 models in our index, averaging 8.402 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 7 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
2
Quantizations
10
Models covered
2
Avg effective bpw
8.402
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | saidutta69 | vs | Theirs | Difference |
|---|---|---|---|---|---|
| c4ai-command-r7b-12-2024 | Q4_K_M | 4.71 GiB | bartowski | 4.71 GiB | -0.0% |
| c4ai-command-r7b-12-2024 | Q5_K_M | 5.40 GiB | bartowski | 5.41 GiB | -0.0% |
| c4ai-command-r7b-12-2024 | Q6_K | 6.14 GiB | bartowski | 6.14 GiB | -0.0% |
| c4ai-command-r7b-12-2024 | Q8_0 | 7.95 GiB | bartowski | 7.95 GiB | -0.0% |
| c4ai-command-r7b-12-2024 | Q4_K_M | 4.71 GiB | oncu | 4.71 GiB | -0.0% |
| MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking | F16 | 2.02 GiB | GnLOLot | 2.02 GiB | 0.0% |
| MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking | Q8_0 | 1.07 GiB | GnLOLot | 1.07 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 |
|---|---|---|
| MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking | 5 | 0.64 GiB |
| c4ai-command-r7b-12-2024 | 5 | 4.71 GiB |