onefrontieronefrontier.ai

google/gemma-4-31B-it

apache-2.0 1 launch

image-text-to-text · 31.27B parameters · 58.3 GiB of weights at revision 842da379. Runs on a single GPU when the source verified it.

download the card performance the weights on HF

Did this card launch? The count is real — it comes from launches the kit recorded against this path, not from a widget anywhere.

1checkpoints
1published launches
1GPU minimum
2named gaps
The identity, read from the HF API at the revision the card pins.
weight pathgoogle/gemma-4-31B-it
revision842da3794eaa0b77d5f08bae87a17459d91ff475
licenseapache-2.0
gatedno
parameters31.27B
weight bytes58.3 GiB
modalityimage-text-to-text
HF downloads8.5M at capture
last modified2026-07-20T16:42:18.000Z

The checkpoints.

Every servable variant in or beside the repo. resident_gib is what lands in VRAM after load; host_gib is what stays on the host and never touches the card.

name format location resident host tier gated
root bf16 repo root 58.3 GiB — no

root — 2 weight file(s)

The published launches.

One entry per engine × checkpoint with a command somebody published. Each cites the page it was read from — the card copies it, it does not invent it.

vllm root

vllm/vllm-openai:latest
argv — what a wrapper execs 
vllm serve google/gemma-4-31B-it --tensor-parallel-size 1 --enable-auto-tool-choice --tool-call-parser gemma4 --chat-template examples/tool_chat_template_gemma4.jinja --reasoning-parser gemma4
as the source printed it
vllm serve google/gemma-4-31B-it \
  --tensor-parallel-size 1 \
  --enable-auto-tool-choice \
  --tool-call-parser gemma4 \
  --chat-template examples/tool_chat_template_gemma4.jinja \
  --reasoning-parser gemma4
validated on
h100, mi300x, mi325x, mi355x, trillium, ironwood, arc_pro_b60, arc_pro_b70
source
vllm-recipes

Every floor a box must clear.

A launch that fails on the third requirement wasted the first two. These are the requirements, as data — the fit gate reads them instead of a paragraph.

The hardware block, verbatim from the card.
GPU modelsh100, mi300x, mi325x, mi355x
architecturescdna3, cdna4, hopper
min GPUs1
TP rulewidest published TP is 1
min VRAM / GPU—
min total VRAM—
min disk120 GiB
min host RAM—
interconnectnot required
CUDA min—
driver min—
context tokens—

The 2 things this card could not answer.

First-class, not swallowed. Every entry is a field a source did not answer — which makes it a launch nobody has done, and therefore a unit of work rather than a defect.

envs.sglang no SGLang cookbook page matched this repo
hardware.npu recipes name non-GPU accelerators too: arc_pro_b60, arc_pro_b70, ironwood, trillium (not carded)

The file.

The card is a YAML document with a published JSON Schema. View it, download it, diff it against the next capture — and point one at it.

download

launch-card.yaml card.json the schema

Same bytes the collector wrote. The JSON is the same card, for a machine that would rather not parse YAML.

with one

one launch --card google/gemma-4-31B-it/launch-card.yaml

one follows the argv above, checks the floors before the paid clock, and on a failure changes exactly one field and retries — recording every attempt against this path.

Where every field came from.

The card is assembled, not authored. These are the sources, so a reader can check the claim rather than trust it.

sourceurl
hf-api https://huggingface.co/api/models/google/gemma-4-31B-it
vllm-recipes https://recipes.vllm.ai/google/gemma-4-31B-it.json

Captured 2026-10-31T17:28:11Z by hf-api + vllm-recipes + sglang-cookbook. Schema onefrontier.launch-card/v1.