Views
No views yet
| Field | Value |
|---|---|
| Base model | source/mistralai--Mixtral-8x7B-Instruct-v0.1 |
| Published artifact | positron-ai/mistralai_Mixtral-8x7B-Instruct-v0.1-tron-best-gptq |
| Quantization method | GPTQ |
| Quantization format | gptq |
| Source precision | n/a |
| Target runtime | n/a |
| Hardware target | n/a |
| Release date | 2026-08-25 |
| License | other |
| Field | Value |
|---|---|
| Weight precision | 4-bit |
| Activation precision | not quantized |
| Bits | 4 |
| Group size | 64 |
| Symmetric quantization | true |
| Activation ordering / desc_act | true |
| Damp percent | 0.05 |
| Calibration dataset | Mixed-domain calibration set |
| Calibration samples | 128 |
| Calibration sequence length | 1024 |
| MoE experts per token | n/a |
| Quantization toolchain | GPTQModel 5.8.0, transformers 4.57.6, torch 2.9.1, CUDA 12.8 |
| Metric | Result | Reference | Notes |
|---|---|---|---|
| Mean KL-divergence | n/a | n/a | Not measured for this release |
| P95 KL-divergence | n/a | n/a | Not measured for this release |
| Top-1 agreement | n/a | n/a | Not measured for this release |
| Perplexity / NLL delta | n/a | n/a | Not measured for this release |
| MMLU mean | 0.8125 | source/mistralai--Mixtral-8x7B-Instruct-v0.1 | MMLU at 10% coverage |
| Field | Value |
|---|---|
| Evaluation date | n/a |
| Evaluation suite | n/a |
| Number of prompts | n/a |
| Runtime | n/a |
| Device | n/a |
| Pass criteria | n/a |