GLM-5
GLM-5 is an open-weights language model from Z.ai, released February 11, 2026. It has 754B parameters (mixture-of-experts, 52B active). The context window is 200K tokens. On the Epoch Capabilities Index it scores 146.5, rank 88 of 256 rated models. API price: $1 input / $3.2 output per million tokens.
We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context …
Check it against your own PC →
Can you run GLM-5 locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. 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 | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: unsloth/GLM-5-GGUF · DevQuasar/zai-org.GLM-5-GGUF · ubergarm/GLM-5-GGUF · QuantTrio/GLM-5-AWQ · amd/GLM-5-NVFP4 · lukealonso/GLM-5-NVFP4
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 43.9 | OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private, FrontierMath-Tier-4-2025-07-01-Private |
| Coding | 49.3 | Terminal Bench, SWE-bench Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| GPQA Diamond | 87.2% |
| OTIS Mock AIME | 80.0% |
| SWE-bench Verified | 72.1% |
| Terminal-Bench | 52.4% |
| SimpleBench | 43.8% |
| FrontierMath-2025-02-28-Private | 28.8% |
| FrontierMath-Tier-4-2025-07-01-Private | 3.5% |
Links
Announcement · Hugging Face: zai-org/GLM-5 · Epoch AI benchmarks
Models with a similar score
DeepSeek-V4-Pro · GPT-5 · Grok 4.3 Beta · Qwen 3.6 Max (Preview) · GPT-5.4 Mini · Qwen 3.6 Plus · Kimi K2.5 · Inkling
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