Quantization publisher
LiteLLMs
LiteLLMs publishes 14 quantizations across 1 models in our index, averaging 5.095 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 5 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
14
Models covered
1
Avg effective bpw
5.095
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | LiteLLMs | vs | Theirs | Difference |
|---|---|---|---|---|---|
| Meta-Llama-3-70B-Instruct | Q4_K_M | 39.61 GiB | lmstudio-community | 39.60 GiB | 0.0% |
| Meta-Llama-3-70B-Instruct | Q4_K_M | 39.61 GiB | qwp4w3hyb | 39.60 GiB | 0.0% |
| Meta-Llama-3-70B-Instruct | Q4_K_S | 37.58 GiB | qwp4w3hyb | 37.58 GiB | 0.0% |
| Meta-Llama-3-70B-Instruct | Q5_K_M | 46.53 GiB | qwp4w3hyb | 46.52 GiB | 0.0% |
| Meta-Llama-3-70B-Instruct | Q5_K_S | 45.32 GiB | qwp4w3hyb | 45.32 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 |
|---|---|---|
| Meta-Llama-3-70B-Instruct | 14 | 24.56 GiB |