onefrontieronefrontier.ai

zai-org/GLM-5.3-Flash

mit 7 launches

image-text-to-text · 321.32B parameters · 305.8 GiB of weights at revision 46a050be. Needs at least 8 GPUs.

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
7published launches
8GPU minimum
1named gaps
The identity, read from the HF API at the revision the card pins.
weight pathzai-org/GLM-5.3-Flash
revision46a050bec13002ad29ee795c16e61cf4fa3c4a9c
licensemit
gatedno
parameters321.32B
weight bytes305.8 GiB
modalityimage-text-to-text
HF downloads6.4M at capture
last modified2026-10-15T06:32:52.000Z

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 305.8 GiB — no

root — 62 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:nightly
argv — what a wrapper execs 
vllm serve zai-org/GLM-5.3-Flash --tokenizer-mode glm5_next --tensor-parallel-size 8 --disable-flashinfer-autotune --tool-call-parser glm47 --enable-auto-tool-choice --reasoning-parser glm47
as the source printed it
vllm serve zai-org/GLM-5.3-Flash \
  --tokenizer-mode glm5_next \
  --tensor-parallel-size 8 \
  --disable-flashinfer-autotune \
  --tool-call-parser glm47 \
  --enable-auto-tool-choice \
  --reasoning-parser glm47
validated on
h100, b200, gb200, mi355x, ascend_950pr_8x
env
VLLM_ENGINE_READY_TIMEOUT_S=3600 · VLLM_USE_RUST_FRONTEND=1
source
vllm-recipes

sglang root

lmsysorg/sglang:latest
argv — what a wrapper execs 
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --encoder-only --host 0.0.0.0 --port 30001
as the source printed it
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --encoder-only --host 0.0.0.0 --port 30001

sglang root

lmsysorg/sglang:latest
argv — what a wrapper execs 
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --attention-backend dsa --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --linear-attn-backend triton --kv-cache-dtype bfloat16 --quantization fp8 --moe-runner-backend flashinfer_trtllm --max-running-requests 64 --chunked-prefill-size 8192 --max-prefill-tokens 8192 --disable-prefill-cuda-graph --speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --language-only --encoder-urls http://localhost:30001 --mem-fraction-static 0.78 --host 0.0.0.0 --port 30000
as the source printed it
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --attention-backend dsa --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --linear-attn-backend triton --kv-cache-dtype bfloat16 --quantization fp8 --moe-runner-backend flashinfer_trtllm --max-running-requests 64 --chunked-prefill-size 8192 --max-prefill-tokens 8192 --disable-prefill-cuda-graph --speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4 --language-only --encoder-urls http://localhost:30001 --mem-fraction-static 0.78 --host 0.0.0.0 --port 30000

sglang root

lmsysorg/sglang:latest
argv — what a wrapper execs 
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --attn-cp-size 4 --enable-prefill-cp --cp-strategy interleave --moe-dense-tp-size 4 --ep-size 1 --speculative-algorithm EAGLE --speculative-num-steps 5 --speculative-eagle-topk 1 --speculative-num-draft-tokens 6 --dsa-prefill-backend trtllm --dsa-decode-backend trtllm --kv-cache-dtype fp8_e4m3 --moe-runner-backend flashinfer_trtllm --reasoning-parser auto --tool-call-parser auto --host 0.0.0.0 --port 30000
as the source printed it
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 4 --attn-cp-size 4 --enable-prefill-cp --cp-strategy interleave --moe-dense-tp-size 4 --ep-size 1 --speculative-algorithm EAGLE --speculative-num-steps 5 --speculative-eagle-topk 1 --speculative-num-draft-tokens 6 --dsa-prefill-backend trtllm --dsa-decode-backend trtllm --kv-cache-dtype fp8_e4m3 --moe-runner-backend flashinfer_trtllm --reasoning-parser auto --tool-call-parser auto --host 0.0.0.0 --port 30000

sglang root

lmsysorg/sglang:latest
argv — what a wrapper execs 
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 2 --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --kv-cache-dtype bfloat16 --moe-runner-backend triton --disaggregation-mode prefill --disaggregation-bootstrap-port 8998 --disaggregation-transfer-backend nixl --host 0.0.0.0 --port 31000
as the source printed it
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 2 --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --kv-cache-dtype bfloat16 --moe-runner-backend triton --disaggregation-mode prefill --disaggregation-bootstrap-port 8998 --disaggregation-transfer-backend nixl --host 0.0.0.0 --port 31000

sglang root

lmsysorg/sglang:latest
argv — what a wrapper execs 
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 2 --base-gpu-id 2 --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --kv-cache-dtype bfloat16 --moe-runner-backend triton --disaggregation-mode decode --disaggregation-transfer-backend nixl --host 0.0.0.0 --port 32000
as the source printed it
sglang serve --model-path zai-org/GLM-5.3-Flash --tp-size 2 --base-gpu-id 2 --dsa-prefill-backend tilelang --dsa-decode-backend tilelang --kv-cache-dtype bfloat16 --moe-runner-backend triton --disaggregation-mode decode --disaggregation-transfer-backend nixl --host 0.0.0.0 --port 32000

sglang root

lmsysorg/sglang:latest
argv — what a wrapper execs 
python -m sglang_router.launch_router --pd-disaggregation --mini-lb --prefill http://127.0.0.1:31000 8998 --decode http://127.0.0.1:32000 --host 0.0.0.0 --port 30000
as the source printed it
python -m sglang_router.launch_router --pd-disaggregation --mini-lb --prefill http://127.0.0.1:31000 8998 --decode http://127.0.0.1:32000 --host 0.0.0.0 --port 30000

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 modelsb200, gb200, h100, mi355x
architecturesblackwell, cdna4, hopper
min GPUs8
TP rulewidest published TP is 8
min VRAM / GPU—
min total VRAM—
min disk417 GiB
min host RAM—
interconnectnot required
CUDA min—
driver min—
context tokens—

The 1 thing 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.

hardware.npu recipes name non-GPU accelerators too: ascend_950pr_8x (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 zai-org/GLM-5.3-Flash/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/zai-org/GLM-5.3-Flash
vllm-recipes https://recipes.vllm.ai/zai-org/GLM-5.3-Flash.json
sglang-cookbook https://docs.sglang.io/cookbook/autoregressive/GLM/GLM-5.3-Flash.md

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