GLM 5.2
753.3B total, 51.2B active · 1024k context · MIT · released 2026-06-16
chatcodingagenticreasoning
In short
GLM 5.2 is an open model from Z.ai with 753.3B parameters (51.2B active per token). At mlx-4bit, GLM 5.2 needs about 391 GB of memory at 8k context and 396 GB at 64k, counting the weights, the KV cache and runtime buffers. Nothing we price in Germany runs GLM 5.2 fully in memory at 64k context at a usable speed; see the table for what comes closest.
Updated . Speeds are estimates; how they are worked out.
What to run it on in Germany
Fully in memory at 64k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File | @8k | @32k | @64k | @128k |
|---|---|---|---|---|---|
| mlx-4bitmlx | 389.6 GB | 391.0 GB | 393.2 GB | 396.2 GB | 402.0 GB |
| UD-Q4_K_Mgguf | 433.8 GB | 435.3 GB | 437.5 GB | 440.4 GB | 446.3 GB |
| UD-Q5_K_Mgguf | 522.3 GB | 523.7 GB | 525.9 GB | 528.9 GB | 534.7 GB |
| UD-Q6_Kgguf | 582.9 GB | 584.3 GB | 586.5 GB | 589.4 GB | 595.3 GB |
| Q8_0gguf | 746.3 GB | 747.8 GB | 750.0 GB | 752.9 GB | 758.7 GB |
Run it
Copy a command for the runtime you use.
- mlx-4bit
- LM Studio
lms get mlx-community/GLM-5.2-4bit - MLX
mlx_lm.server --model mlx-community/GLM-5.2-4bit
- LM Studio
- UD-Q4_K_M
- Ollama
ollama run hf.co/unsloth/GLM-5.2-GGUF:UD-Q4_K_M - LM Studio
lms get unsloth/GLM-5.2-GGUF@ud-q4_k_m - llama.cpp
llama-server -hf unsloth/GLM-5.2-GGUF:UD-Q4_K_M
- Ollama
- UD-Q5_K_M
- Ollama
ollama run hf.co/unsloth/GLM-5.2-GGUF:UD-Q5_K_M - LM Studio
lms get unsloth/GLM-5.2-GGUF@ud-q5_k_m - llama.cpp
llama-server -hf unsloth/GLM-5.2-GGUF:UD-Q5_K_M
- Ollama
- UD-Q6_K
- Ollama
ollama run hf.co/unsloth/GLM-5.2-GGUF:UD-Q6_K - LM Studio
lms get unsloth/GLM-5.2-GGUF@ud-q6_k - llama.cpp
llama-server -hf unsloth/GLM-5.2-GGUF:UD-Q6_K
- Ollama
- Q8_0
- Ollama
ollama run hf.co/unsloth/GLM-5.2-GGUF:Q8_0 - LM Studio
lms get unsloth/GLM-5.2-GGUF@q8_0 - llama.cpp
llama-server -hf unsloth/GLM-5.2-GGUF:Q8_0
- Ollama
Notes
Needs SGLang v0.5.13.post1+ or vLLM v0.23.0+ to serve; the card marks it superseded by zai-org/GLM-5.3-BF16. Has multiple thinking-effort levels and an MTP layer for speculative decoding. Sparse or compressed attention: KV read per token is estimated as full attention.
Questions
- How much VRAM does GLM 5.2 need?
- At mlx-4bit, GLM 5.2 needs about 391 GB of memory at 8k context and 396 GB at 64k, counting the weights, the KV cache and runtime buffers.
- Can I run GLM 5.2 on a 16 GB GPU?
- No: it does not fit in 16 GB at 64k context, even with system RAM.
- Can I run GLM 5.2 on a 24 GB GPU?
- No: it does not fit in 24 GB at 64k context, even with system RAM.
- How do I run GLM 5.2 locally?
- With Ollama: ollama run hf.co/unsloth/GLM-5.2-GGUF:UD-Q4_K_M (the UD-Q4_K_M build). LM Studio and llama.cpp commands are on this page.
- What licence is GLM 5.2 released under?
- MIT, which allows commercial use.