GLM-4.7-Flash
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Reasoning can be off
- Tool use
- Structured output
- Open weights
Prices
3 offerings · prices as listedGLM-4.7-Flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | Free | Free | Free |
Prices from Pricing (opens in a new tab) (checked Nov 1, 2026)
GLM-4.7-Flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | Free | Free | Free |
Prices from 智谱 BigModel：API 定价 (opens in a new tab) (checked Nov 2, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Knowledge cutoff
- Apr 2025
- Licence
- mit
- Family
- glm-flash
- 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-4.7-Flash- Parameters 31.2B
- Active 5.2B (estimated) · 64 experts, 4 per token
- Native precision BF16
- Layers 47
- KV cache per token 53 KB
- Config positions 198K (config.json max_position_embeddings)
- API context 195K (maker’s API)
- Needs
- ≈ 19.0 GB (weights 17.7 + KV cache 0.4 + overhead 0.9)
- Usable
- 21.6 GB (90% of its memory)
- Generation speed
- 140–211 tok/s (reads the active 5.2B per token)
- Longest context
- 59K (longer doesn’t fit)
- First token
- about 0.17–0.25 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 58.2 GB | ≈ 61.5 | ○Needs system memory 11–16 tok/s | — |
| Q8_0 | 30.9 GB | ≈ 32.9 | ○Needs system memory 21–31 tok/s | — |
| FP8 | 29.1 GB | ≈ 30.9 | ○Needs system memory 22–33 tok/s | — |
| Q6_K | 23.9 GB | ≈ 25.5 | ○Needs system memory 43–65 tok/s | — |
| Q5_K_M | 20.7 GB | ≈ 22.1 | ○Needs system memory 95–143 tok/s | — |
| Q5_0 | 20.0 GB | ≈ 21.4 | ●Runs well 126–189 tok/s | 12K |
| Q4_K_M | 17.7 GB | ≈ 19.0 | ●Runs well 140–211 tok/s | 59K |
| Q4_0 | 16.4 GB | ≈ 17.6 | ●Runs well 150–225 tok/s | 86K |
| IQ4_XS | 15.4 GB | ≈ 16.6 | ●Runs well 158–237 tok/s | 104K |
| Q3_K_Mquality drops | 14.2 GB | ≈ 15.3 | ●Runs well 170–254 tok/s | 129K |
| IQ3_XXSquality drops | 11.1 GB | ≈ 12.1 | ●Runs well 208–312 tok/s | 192K |
| Q2_Kquality drops | 10.9 GB | ≈ 11.9 | ●Runs well 211–317 tok/s | 195K |
| IQ2_XXSquality drops | 7.5 GB | ≈ 8.4 | ●Runs well 284–426 tok/s | 195K |
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): GPU GeForce RTX 4090; unified memory Apple M6 (24GB or 32GB) · 32 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 1,365
#120 of 163 listed models · CI 1,359–1,370 · 12,008 votes
- Epoch AI · GPQA Diamond 60.5%
#111 of 168 listed models · ±2.93
Also listed: reasoning off 45.1%
- Epoch AI · OTIS Mock AIME 2024–2025 58.3%
#104 of 159 listed models · ±6.56
Also listed: reasoning off 25%
- EQ-Bench Creative Writing v3 1,139
#78 of 93 listed models
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 28, 2026
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Nov 4, 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 →- Now priced on Cloudflare Workers AI Input $0.060 · Output $0.40
- Now priced on Z.ai API, China Input Free · Output Free · Cache read Free
Sources
- Pricing (opens in a new tab) docs.z.ai · checked Nov 1, 2026
- 智谱 BigModel：API 定价in Chinese (opens in a new tab) docs.bigmodel.cn · checked Nov 2, 2026
- 智谱 BigModel：GLM-4.7-FLASHin 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-4.7-Flash model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- models.dev: glm-4.7-flash (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- zai-org/GLM-4.7-Flash model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
- Cloudflare Workers AI pricing (opens in a new tab) developers.cloudflare.com · checked Oct 31, 2026
- zai-org/GLM-4.7-Flash model card (opens in a new tab) huggingface.co · checked Oct 30, 2026
- zai-org/GLM-4.7-Flash config.json (opens in a new tab) huggingface.co · checked Oct 30, 2026
- zai-org/GLM-4.7-Flash files (opens in a new tab) huggingface.co · checked Nov 4, 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