GLM-4.5
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Structured output
- Open weights
Prices
1 offering · prices as listedglm-4.5| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $0.60 | $0.11 | $2.20 |
Prices from Pricing (opens in a new tab) (checked Nov 1, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Knowledge cutoff
- Apr 2025
- Licence
- MIT open-source license
- Family
- glm
- Model ID
Not stated on Zhipu AI’s pages: max input, reasoning efforts, max thinking budget, built-in tools, aliases.
Run locally
Weights: zai-org/GLM-4.5- Parameters 358.3B
- Active 39.2B (estimated) · 160 experts, 8 per token
- Native precision BF16
- Layers 92
- KV cache per token 368 KB
- Config positions 128K (config.json max_position_embeddings)
- API context 125K (maker’s API)
- Needs
- ≈ 189.0 GB (weights 177.3 + KV cache 2.9 + overhead 8.9)
- Usable
- 21.6 GB (90% of its memory)
- Try
- it’s too large for this hardware; see the smallest that runs it below
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 667.5 GB | ≈ 703.7 | ✕Doesn’t fit | — |
| Q8_0 | 354.6 GB | ≈ 375.2 | ✕Doesn’t fit | — |
| FP8maker’s file | 336.5 GB | ≈ 356.2 | ✕Doesn’t fit | — |
| Q6_K | 274.1 GB | ≈ 290.7 | ✕Doesn’t fit | — |
| Q5_K_M | 237.4 GB | ≈ 252.1 | ✕Doesn’t fit | — |
| Q5_0 | 229.4 GB | ≈ 243.8 | ✕Doesn’t fit | — |
| Q4_K_M | 202.7 GB | ≈ 215.8 | ✕Doesn’t fit | — |
| Q4_0 | 187.7 GB | ≈ 200.0 | ✕Doesn’t fit | — |
| IQ4_XS | 177.3 GB | ≈ 189.0 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 163.1 GB | ≈ 174.1 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 127.7 GB | ≈ 136.9 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 125.1 GB | ≈ 134.3 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 85.9 GB | ≈ 93.1 | ✕Doesn’t fit | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): no single listed GPU; unified memory Apple M5 Ultra (80-core GPU) · 512 GB.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- LMArena Text 1,411
#93 of 163 listed models · CI 1,406–1,416 · 23,797 votes
- EQ-Bench Creative Writing v3 1,344
#71 of 93 listed models
- EQ-Bench Longform Writing 55.5
#71 of 92 listed models
- LMArena Text · Chinese 1,431
#98 of 161 listed models · CI 1,417–1,446 · 1,785 votes
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 28, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 28, 2026
- changes we made
Changes
All changes →No changes recorded yet.
Sources
- Pricing (opens in a new tab) docs.z.ai · checked Nov 1, 2026
- 智谱 BigModel：GLM-4.5in Chinese (opens in a new tab) docs.bigmodel.cn · checked Nov 1, 2026
- New Released (opens in a new tab) docs.z.ai · checked Oct 10, 2026
- zai-org/GLM-4.5 model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- models.dev: glm-4.5 (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- zai-org/GLM-4.5 model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- zai-org/GLM-4.5 model card (opens in a new tab) huggingface.co · checked Oct 30, 2026
- zai-org/GLM-4.5 config.json (opens in a new tab) huggingface.co · checked Nov 2, 2026
- zai-org/GLM-4.5 files (opens in a new tab) huggingface.co · checked Nov 2, 2026
- zai-org/GLM-4.5-FP8 files (opens in a new tab) huggingface.co · checked Nov 2, 2026
Zhipu AI’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Zhipu AI · China · z.ai
Related models
Snapshots, the same family and other models from this provider