Model reference · open weights

GLM-5.3-Flash

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.

NEW · released this week LLMs unsloth 3 variants 46k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What GLM-5.3-Flash is

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

What it is

Makerunsloth
TypeLanguage models
Variants3
Based onzai-org/GLM-5.3-Flash
Released2026-08-26
Popularity46k downloads / month
Likes296
LicenceOpen weights

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.

Variants

Sizes & precisions

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.

VariantParamsPrecisionVRAMFits 16 GBWeights
GLM-5.3-Flash-GGUFGGUFWeights ↗
GLM-5.3-Flash-FP8321.3BFP8~369.5 GBWeights ↗
GLM-5.3-Flash321.3BBF16~739 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

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"}]}'

Details

Languages, data & research

Languages

en zh

Tags

gguf unsloth glm5_next text-generation en zh endpoints_compatible conversational transformers safetensors image-text-to-text fp8

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want GLM-5.3-Flash on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More language models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms