Can I run GLM 4.5V locally?
GLM 4.5V by zai-org has 108B parameters (14B active per token, 128 experts, 8 used per token). At 4-bit with an 8K context it needs about 61.4 GB of GPU memory. It fits on 22 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 ggml-org/GLM-4.5V-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx |
|---|---|---|---|---|
| 2-bit (Q2_K) | rough | 39.0 GB | 39.7 GB | 44.1 GB |
| 3-bit (Q3_K_M) | usable | 50.4 GB | 51.2 GB | 55.5 GB |
| 4-bit (Q4_K_M) • | good, most popular | 60.7 GB | 61.4 GB | 65.7 GB |
| 5-bit (Q5_K_M) | very good | 72.9 GB | 73.6 GB | 77.9 GB |
| 6-bit (Q6_K) | near lossless | 83.7 GB | 84.4 GB | 88.7 GB |
| 8-bit (Q8_0) • | effectively lossless | 107 GB | 108 GB | 112 GB |
| 16-bit (F16/BF16) | original weights | 202 GB | 203 GB | 207 GB |
Which GPUs and Macs run GLM 4.5V?
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 4.5V is on OpenRouter at $0.60 per 1M input tokens and $1.80 per 1M output tokens. Price details and history →
Questions
How much VRAM does GLM 4.5V need?
About 61.4 GB at 4-bit (Q4_K_M) with an 8K context: 59.3 GB of weights (real GGUF file size), 1.4 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 108 GB.
What is the smallest GPU that runs GLM 4.5V?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the H100 PCIe (80 GB).
Can I run GLM 4.5V on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M2 Max 96GB or larger, using the default macOS GPU memory limit.
Model facts
| Hugging Face repo | zai-org/GLM-4.5V |
| Parameters | 107,710,933,120 (108B) · ~14B active (computed from config) |
| Layers / hidden size | 46 / 4096 |
| Attention | GQA; 96 heads, 8 KV heads, head dim 128 |
| KV cache per token (FP16) | 184.0 KiB |
| Max context | 65,536 tokens |
| License | mit |
| Released on HF | Aug 10, 2025 |
| Downloads (30d) / likes | 14,901 / 726 |
Sources: Hugging Face model API · config.json (zai-org/GLM-4.5V) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.