Can I run GLM 5.3 Flash locally?
GLM 5.3 Flash by zai-org has 321B parameters (18B active per token, 288 experts, 8 used per token). At 4-bit with an 8K context it needs about 184 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-5.3-Flash-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 | 113 GB | 113 GB | 113 GB | 115 GB |
| 3-bit (Q3_K_M) | usable | 147 GB | 147 GB | 147 GB | 149 GB |
| 4-bit (Q4_K_M) | good, most popular | 184 GB | 184 GB | 184 GB | 185 GB |
| 5-bit (Q5_K_M) | very good | 214 GB | 214 GB | 214 GB | 216 GB |
| 6-bit (Q6_K) | near lossless | 246 GB | 246 GB | 247 GB | 248 GB |
| 8-bit (Q8_0) • | effectively lossless | 318 GB | 318 GB | 319 GB | 320 GB |
| 16-bit (F16/BF16) • | original weights | 598 GB | 598 GB | 599 GB | 600 GB |
Which GPUs and Macs run GLM 5.3 Flash?
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 5.3 Flash is on OpenRouter at $0.0399 per 1M input tokens and $0.0784 per 1M output tokens. Price details and history →
Questions
How much VRAM does GLM 5.3 Flash need?
About 184 GB at 4-bit (Q4_K_M) with an 8K context: 183 GB of weights (estimated), 0.1 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 318 GB.
What is the smallest GPU that runs GLM 5.3 Flash?
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 5.3 Flash 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-5.3-Flash |
| Parameters | 321,323,031,390 (321B) · ~18B active (computed from config) |
| Layers / hidden size | 45 / 4096 |
| Attention | MLA (hybrid: 34 linear/state layers); 64 heads, 64 KV heads, head dim 64 |
| KV cache per token (FP16) | 13.8 KiB |
| Max context | 1,048,576 tokens |
| License | mit |
| Released on HF | Aug 25, 2026 |
| Downloads (30d) / likes | 6,373,257 / 3,241 |
Sources: Hugging Face model API · config.json (zai-org/GLM-5.3-Flash) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.