This is a copy of mgoin/Minitron-4B-Base-FP8 at commit e2f62cf, made on 2026-10-30. vLLM CI uses this checkpoint and the original is on a personal account, so we keep a copy here to reduce supply-chain risk.

Minitron-4B-Base-FP8

FP8 quantized checkpoint of nvidia/Minitron-4B-Base for use with vLLM.

lm_eval --model vllm --model_args pretrained=mgoin/Minitron-4B-Base-FP8 --tasks gsm8k --num_fewshot 5 --batch_size auto

vllm (pretrained=mgoin/Minitron-4B-Base-FP8), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.2305|±  |0.0116|
|     |       |strict-match    |     5|exact_match|↑  |0.2282|±  |0.0116|

Downloads last month: 18

Safetensors

Model size

4B params

Tensor type

BF16

F8_E4M3

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for vllm-project/Minitron-4B-Base-FP8

Base model

nvidia/Minitron-4B-Base

Quantized

(12)

this model

Collection including vllm-project/Minitron-4B-Base-FP8

CI

Collection

Models used in vLLM CI, last updated 2026-10-30. Checkpoints from personal accounts are copied here to reduce supply-chain risk. • 224 items • Updated about 19 hours ago