Can I run GLM 4.5 locally?
GLM 4.5 by zai-org has 358B parameters (36B active per token, 160 experts, 8 used per token). At 4-bit with an 8K context it needs about 205 GB of GPU memory. It fits on 4 of 65 GPUs and Macs we track.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from unsloth/GLM-4.5-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx | 128K ctx |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | rough | 124 GB | 126 GB | 134 GB | 169 GB |
| 3-bit (Q3_K_M) • | usable | 162 GB | 163 GB | 172 GB | 206 GB |
| 4-bit (Q4_K_M) • | good, most popular | 204 GB | 205 GB | 214 GB | 248 GB |
| 5-bit (Q5_K_M) • | very good | 239 GB | 240 GB | 249 GB | 283 GB |
| 6-bit (Q6_K) • | near lossless | 276 GB | 278 GB | 286 GB | 321 GB |
| 8-bit (Q8_0) • | effectively lossless | 357 GB | 358 GB | 367 GB | 401 GB |
| 16-bit (F16/BF16) • | original weights | 670 GB | 671 GB | 680 GB | 714 GB |
Which GPUs and Macs run GLM 4.5?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
Prefer an API?
Z.ai: GLM 4.5 is on OpenRouter at $0.60 per 1M input tokens and $2.20 per 1M output tokens. Price details and history →
Questions
How much VRAM does GLM 4.5 need?
About 205 GB at 4-bit (Q4_K_M) with an 8K context: 202 GB of weights (real GGUF file size), 2.9 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 358 GB.
What is the smallest GPU that runs GLM 4.5?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the Mac M3 Ultra 512GB (512 GB).
Can I run GLM 4.5 on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M3 Ultra 512GB or larger, using the default macOS GPU memory limit.
Model facts
| Hugging Face repo | zai-org/GLM-4.5 |
| Parameters | 358,337,791,296 (358B) · ~36B active (computed from config) |
| Layers / hidden size | 92 / 5120 |
| Attention | GQA; 96 heads, 8 KV heads, head dim 128 |
| KV cache per token (FP16) | 368.0 KiB |
| Max context | 131,072 tokens |
| License | mit |
| Released on HF | Jul 20, 2025 |
| Downloads (30d) / likes | 119,750 / 1,439 |
Sources: Hugging Face model API · config.json (zai-org/GLM-4.5) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.