Can I run GLM 4.6V locally?
GLM 4.6V 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 68.6 GB of GPU memory. It fits on 22 of 65 GPUs and Macs we track.
Image input needs the vision projector file too: about 1.6 GB more (bartowski/zai-org_GLM-4.6V-GGUF), not included in the figures below, which are for text-only use.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from bartowski/zai-org_GLM-4.6V-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 | 43.0 GB | 43.8 GB | 48.1 GB | 65.3 GB |
| 3-bit (Q3_K_M) • | usable | 51.5 GB | 52.2 GB | 56.6 GB | 73.8 GB |
| 4-bit (Q4_K_M) • | good, most popular | 67.9 GB | 68.6 GB | 72.9 GB | 90.1 GB |
| 5-bit (Q5_K_M) • | very good | 77.0 GB | 77.7 GB | 82.0 GB | 99.3 GB |
| 6-bit (Q6_K) • | near lossless | 90.7 GB | 91.4 GB | 95.7 GB | 113 GB |
| 8-bit (Q8_0) • | effectively lossless | 107 GB | 108 GB | 112 GB | 129 GB |
| 16-bit (F16/BF16) | original weights | 202 GB | 203 GB | 207 GB | 224 GB |
Which GPUs and Macs run GLM 4.6V?
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 4.6V is on OpenRouter at $0.30 per 1M input tokens and $0.90 per 1M output tokens. Price details and history →
Questions
How much VRAM does GLM 4.6V need?
About 68.6 GB at 4-bit (Q4_K_M) with an 8K context: 66.5 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 4.6V?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the RTX PRO 6000 Blackwell (96 GB).
Can I run GLM 4.6V on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M3 Max 128GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
GLM 4.5V
108B · 61.4 GB at 4-bitGLM 4.5 Air
110B · 70.6 GB at 4-bitGLM Z1 32B 0414
33B · 19.5 GB at 4-bitLing 2.6 Flash
107B · 62.2 GB at 4-bitLlama 4 Scout 17B 16E Instruct
109B · 65.2 GB at 4-bitgpt-oss 120B
117B · 59.6 GB at 4-bitEmbed this
Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.
Copy a snippet
Markdown badge
[](https://runsonmy.com/model/glm-4-6v/) Widget (script)
<div class="runsonmy-widget" data-model="glm-4-6v"><a href="https://runsonmy.com/model/glm-4-6v/">Will GLM 4.6V run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script> Widget (iframe)
<iframe src="https://runsonmy.com/embed/m/glm-4-6v/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will GLM 4.6V run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | zai-org/GLM-4.6V |
| 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 | 131,072 tokens |
| License | mit |
| Released on HF | Dec 7, 2025 |
| Downloads (30d) / likes | 6,099 / 398 |
Sources: Hugging Face model API · config.json (zai-org/GLM-4.6V) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.