GLM-4.7-Flash
GLM-4.7-Flash is an open-weights language model from Z.ai, released January 19, 2026. It has 31B parameters (mixture-of-experts, 5.2B active). The context window is 195K tokens. API price: $0 input / $0 output per million tokens.
GLM-4.7, your new coding partner, is coming with the following features: Core Coding: GLM-4.7 brings clear gains, compared to its predecessor GLM-4.6, in multilingual agentic coding and terminal-based tasks, including (73.8%, +5.8%) on SWE-bench, (66.7%, +12.9%) on SWE-bench Multilingual, and (41%, +16.5%) on Terminal …
Check it against your own PC →
Can you run GLM-4.7-Flash locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, GPU + experts in RAM, roughly 14 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 5.2 GB | 21.9 GB | ~14 |
| 8 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 7.2 GB | 19.9 GB | ~16 |
| 12 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 11.2 GB | 15.9 GB | ~20 |
| 16 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 15.2 GB | 11.9 GB | ~25 |
| 24 GB VRAM | Runs on GPU | Q4_K_M (very good) | 20.6 GB | – | ~150 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 27.1 GB | – | ~200 |
Ready-made quantizations on Hugging Face: unsloth/GLM-4.7-Flash-GGUF · lmstudio-community/GLM-4.7-Flash-GGUF · bartowski/zai-org_GLM-4.7-Flash-GGUF · ggml-org/GLM-4.7-Flash-GGUF · ThalisAI/GLM-4.7-Flash-heretic · QuantTrio/GLM-4.7-Flash-AWQ
Benchmark results
Epoch AI has not published results for GLM-4.7-Flash yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: zai-org/GLM-4.7-Flash
More from Z.ai
GLM-5.3-FlashX · GLM 5.3 Flash BF16 · GLM 5.3 BF16 · GLM-5.3-Flash · GLM-5.3 · GLM-5.2 · GLM-5.1 · GLM-5V-Turbo