Model reference · open weights
GLM-5.3-Flash is an open-weight language model from unsloth, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Read our How to Run GLM-5.3-Flash Guide! GLM-5.3-Flash 👋 Join our <a href="https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/wechat.png" target="blank"WeChat</a or <a href="https://discord.gg/QR7SARHRxK" target="blank"Discord</a community. 📖 Check out the GLM-5.3-Flash <a href="https://z.ai/blog/glm-5.3-flash" target="blank"blog</a and GLM-5 <a href="https://arxiv.org/abs/2602.15763" target="blank"Technical report</a. 📍 Use GLM-5.3-Flash API services on <a href="https://docs.z.ai/guides/llm/glm-5.3-flash"Z.ai API Platform. </a Introduction We introduce GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks. GLM-5.3-Flash starts from a newly trained base model, with its architecture and training recipe redesigned around capability and efficiency. For the first time in the GLM series, we introduce a hybrid architecture combining sparse and linear attention, sharply reducing long-context serving costs while preserving precise long-context capabilities. The model also adopts Manifold-Constrained Hyper-Connections (mHC) to further improve scaling efficiency. Together with our latest 30T-token multimodal pre-training corpus, these changes enable GLM-5.3-Flash to deliver more intelligence with less compute. Footnotes HLE w/ tools (full set): We use sampling parameters of temperature=1.0 and topp=0.95 for evaluation, with a maximum generation length of 163,840 tokens. The evaluation is conducted with a maximum context length of 300,000 tokens, using a context management strategy. We use GPT-5.6-luna (medium) as the judge model. NL2Repo: We evaluated NL2Repo with temperature=1.0, topp=1.0, and maxnewtokens=64k under 1M context. To prevent hacking, we use rule-based and a LLM-based judgement to prevent malicious behaviors (e.g., unauthorized pip or curl operations). DeepSWE: We run DeepSWE using the mini-swe-agent harness with temperature=0.95, topp=1.0, timeout=6h and 400K context. Terminal-Bench 2.1: We evaluate in Cl
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | unsloth |
|---|---|
| Type | Language models |
| Variants | 3 |
| Based on | zai-org/GLM-5.3-Flash |
| Released | 2026-08-26 |
| Popularity | 46k downloads / month |
| Likes | 296 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys unsloth-glm-5-3-flash for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (unsloth-glm-5-3-flash below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"unsloth-glm-5-3-flash","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗