GLM-5.3: VRAM requirements by quant
Key facts
GLM-5.3 needs about 469.6 GB at standard quality (Q4, estimate).
Checked . Unsloth UD-Q4_K_XL GGUF.
GLM-5.3 is a very large open AI model. It needs about 470 GB of memory at standard quality, more than any PC or Mac we track. Models this size usually run on rented servers.
LIVE IN BROWSER · $0 · NO LOGIN
Test comparable open models (Recursive Flint 40B vs Gemma 4 31B) free in your browser
Open full 8-model playground ↗Click a starter prompt below or type your own question to watch Recursive Flint stream side by side against Gemma 4 31B right on this page:
Memory needed
About 470 GB
At standard quality, with room for a conversation of about 12 pages.
Cheapest machine that runs it
None of ours
It needs more than any PC or Mac we track.
THE FIT LIST · FREE
Will the next model beat GLM-5.3 on your 128 GB? We'll tell you when it lands.
GLM-5.3 needs 469.6 GB at Q4. When a new open model would fit 128 GB, or the cards and Macs that run it change price, The Fit List tells you, with the memory it needs and dated EU/US prices. Plus a free GPU buying cheat sheet (PDF) now.
Can a PC or Mac run GLM-5.3?
None of the PCs or Macs we track can hold GLM-5.3: it needs about 470 GB. Models this size usually run on rented servers. What renting costs
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate
Memory at each quality level
A lower quality level makes the model smaller, so it fits on a smaller machine. Standard (Q4) is what most people run.
| Quality | Memory needed |
|---|---|
| Q4 · standard (smallest that keeps quality) | 469.6 GB |
| Q5 · a bit sharper, a bit bigger | 537.1 GB |
| Q8 · near full quality, almost twice Q4 | 808.3 GB |
| FP16 · full quality, over three times Q4 | 1,508.9 GB |
With a conversation of 8,192 tokens · about 12 pages of text.
Sources and method
At standard quality: 467.3 GB for the model itself (a measured file), 1.5 GB for a conversation of 8,192 tokens, and 0.8 GB for the software.
Size source: huggingface.co/zai-org/GLM-5.3. 753.33B parameters in total, 40B used for each word. The memory counts the total.
Z.ai's open-weight sparse mixture of experts (GLM-5.3 License: MIT-style and permissive, plus a Model-as-a-Service clause: MaaS businesses with more than US$10 billion revenue in the past 12 months need Z.AI's security review before commercial use). Hugging Face safetensors metadata lists 753,329,940,480 parameters (F8_E4M3 751.23B, BF16 2.10B), stored here as 753.33B, so our count is an estimate. About 40B are active per token (Artificial Analysis lists 753B total / 40B active; Unsloth's guide says 744B). Config: GlmMoeDsaForCausalLM, 78 layers (first 3 dense), hidden size 6144, 64 attention heads, 256 routed experts plus 1 shared, 8 routed per token, 1 MTP layer, text only, max_position_embeddings 1,048,576. Attention is MLA (kv_lora_rank 512 + qk_rope_head_dim 64 = 576 cached values per token per layer) with a DeepSeek-style sparse indexer (32 index heads x 128, top-k 2048). We store kvHeads 1 and headDim 576, so our K+V formula gives 1.47 GB at 8,192 tokens. A runtime that caches only the 576-wide latent needs about half (0.74 GB in BF16); the indexer key cache is not counted. Our figure is a conservative estimate. Q4 uses the measured Unsloth UD-Q4_K_XL file, 467.29 GB (467,289,116,837 bytes). Q5, Q8 and FP16 are our bytes-per-parameter estimates (0.71 / 1.07 / 2.0 x 753.33B). Unsloth GGUF sizes, shards summed from the Hugging Face tree, decimal GB, checked 29 Oct 2026 (https://huggingface.co/unsloth/GLM-5.3-GGUF): UD-IQ1_S 216.72, UD-IQ1_M 228.49, UD-IQ2_M 238.58, UD-Q2_K_XL 253.88, UD-IQ3_XXS 281.69, UD-Q3_K_XL 342.97, UD-IQ4_XS 365.31, UD-Q4_K_XL 467.29, UD-Q5_K_XL 562.47, UD-Q6_K_XL 684.37, Q8_0 801.36, BF16 1,507.99. Smallest full-model file we found: antirez/glm-5.3-gguf IQ2_XXS mix, 211.08 GB (https://huggingface.co/antirez/glm-5.3-gguf). MLX: mlx-community/GLM-5.3-4bit 418.32 GB; pipenetwork/GLM-5.3-MLX-mixed-3_6bit 332.58 GB. NVIDIA NVFP4 checkpoint 464.14 GB (https://huggingface.co/nvidia/GLM-5.3-NVFP4). Official FP8 weights are 755.63 GB; BF16 repo zai-org/GLM-5.3-BF16 is 1,506.67 GB. Pruned derivatives with experts removed are not GLM-5.3 and are not scored. Runs in mainline llama.cpp per Unsloth's guide (https://unsloth.ai/docs/models/glm-5.3). Unsloth says UD-IQ2_M works on 256 GB RAM devices such as 2x DGX Spark or a Mac Studio; that is a vendor claim, not tested by us, and it relies on RAM offload. With 192 GB usable on a 256 GB Mac Studio M5 Ultra, even the 211.08 GB file does not fit, so no machine on our list runs GLM-5.3 fully in fast memory. Released by Z.ai on 18 August 2026 (API; docs.z.ai release notes and Artificial Analysis), with the Hugging Face repo created 25 August 2026. Artificial Analysis Intelligence Index v5.0: 32 for GLM-5.3 (max), checked 29 Oct 2026 (https://artificialanalysis.ai/models/glm-5-3). Thinking is always on (low / high / max). Ollama tag: not checked.
Licence
Commercial use: yes, with limits
Model-as-a-Service businesses over US$10 billion revenue in 12 months need Z.AI's security review before commercial use.
Licence: GLM-5.3 License · checked 29 Oct 2026
Our reading of the licence, not legal advice.
Will GLM-5.3 run on my graphics card?
Common questions
- How much memory does GLM-5.3 need?
- About 469.6 GB at standard quality (Q4) with a conversation of 8,192 tokens: 467.3 GB for the model itself, 1.5 GB for the conversation and 0.8 GB for the software. The model size is a measured file; the conversation and software parts are our estimate.
- Does GLM-5.3 fit on a single 24 GB graphics card?
- Not in full. It needs about 469.6 GB, and a 24 GB card leaves about 23.4 GB usable.
- Are the speeds measured?
- We do not show a speed for this model. It is a mixture-of-experts model, and our estimate would not be reliable for that design.
- Can I run GLM-5.3 locally?
- Not fully in fast memory on any machine we list. GLM-5.3 has about 753B parameters (40B active), and the smallest full-model file we found is 211.08 GB (a community IQ2_XXS GGUF). With 8,192 tokens of context that needs about 213 GB, more than the 192 GB usable on a 256 GB Mac Studio M5 Ultra.
- How much memory does GLM-5.3 need at 4-bit?
- Unsloth's UD-Q4_K_XL GGUF is 467.29 GB, so our estimate is about 469.56 GB with 8,192 tokens of context and working space. Unsloth's own guide gives 372–475 GB for its 4-bit files.
- What is the smallest GLM-5.3 file?
- The smallest full-model files we found on 29 Oct 2026 are antirez/glm-5.3-gguf at 211.08 GB and Unsloth UD-IQ1_S at 216.72 GB. Pruned versions with experts removed are smaller but are not GLM-5.3 itself, so we do not score them.
- Can GLM-5.3 run on 2× DGX Spark or a 256 GB Mac?
- Unsloth says its UD-IQ2_M file (238.58 GB) works on 256 GB RAM devices such as 2× DGX Spark or a Mac Studio. That is a vendor claim we have not tested. On our rule a 256 GB Mac has about 192 GB usable, so we do not score it as a full fit.
- How good is GLM-5.3?
- Artificial Analysis gives GLM-5.3 (max) 32 on its Intelligence Index v5.0, checked 29 Oct 2026. Thinking is always on, with low, high and max settings.
- Is GLM-5.3 free for commercial use?
- The GLM-5.3 License is permissive and MIT-style. It adds one condition: Model-as-a-Service businesses with more than US$10 billion in revenue over the past 12 months need Z.ai's security review before commercial use. Read the licence before you ship.