GLM 4.5V
107.7B total, 14.3B active · 64k context · MIT · released 2025-08-11
visionreasoningagenticchat
In short
GLM 4.5V is an open model from Z.ai with 107.7B parameters (14.3B active per token). At Q4_K_M, GLM 4.5V needs about 61 GB of memory at 8k context and 61 GB at 8k, counting the weights, the KV cache and runtime buffers. The cheapest hardware in the US that runs GLM 4.5V fully in memory at 8k context is the Mac Studio M3 Ultra 96GB, $4,399 at eBay, at about 32 tok/s (estimated).
Updated . Speeds are estimates; how they are worked out.
What to run it on in the US
Fully in memory at 8k context, priced at retailers today.
Cheapest
Mac Studio M3 Ultra 96GB32tok/sest.Q4_K_M
$4,399
Best value
NVIDIA RTX PRO 6000 Blackwell67tok/sest.Q4_K_M
$7,997
Fastest
NVIDIA RTX PRO 6000 Blackwell67tok/sest.Q4_K_M
$7,997
Mac
Mac Studio M3 Ultra 96GB32tok/sest.Q4_K_M
$4,399
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
| Hardware | Quant | Fits | Decode | Price | tok/s per 1,000 |
|---|---|---|---|---|---|
| Framework Desktop Ryzen AI Max+ 395 128GB | Q4_K_M | fits | 9 tok/s | $3,449 | 2.5 |
| GMKtec EVO-X2 Ryzen AI Max+ 395 128GB | Q4_K_M | fits | 9 tok/s | $3,650 | 2.3 |
| Mac Studio M3 Ultra 96GB | Q4_K_M | fits | 32 tok/s | $4,399 | 7.3 |
| Mac Studio M4 Max 128GB | Q4_K_M | fits | 21 tok/s | $4,999 | 4.3 |
| ASUS Ascent GX10 128GB | Q8_0 | fits | 6 tok/s | $6,100 | 1.0 |
| NVIDIA DGX Spark 128GB | Q8_0 | fits | 6 tok/s | $7,399 | 0.8 |
| NVIDIA RTX PRO 6000 Blackwell | Q4_K_M | fits | 67 tok/s | $7,997 | 8.4 |
| Mac Studio M3 Ultra 256GB | Q8_0 | fits | 19 tok/s | $8,499 | 2.3 |
| Mac Studio M3 Ultra 512GB | Q8_0 | fits | 19 tok/s | $23,000 | 0.8 |
31 other cards and machines we price cannot hold 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 |
|---|---|---|---|---|
| Q4_K_Mgguf | 59.3 GB | 61.4 GB | 65.9 GB | 71.8 GB |
| Q8_0gguf | 105.8 GB | 108.0 GB | 112.4 GB | 118.4 GB |
Run it
Copy a command for the runtime you use.
- Q4_K_M
- Ollama
ollama run hf.co/ggml-org/GLM-4.5V-GGUF:Q4_K_M - LM Studio
lms get ggml-org/GLM-4.5V-GGUF@q4_k_m - llama.cpp
llama-server -hf ggml-org/GLM-4.5V-GGUF:Q4_K_M
- Ollama
- Q8_0
- Ollama
ollama run hf.co/ggml-org/GLM-4.5V-GGUF:Q8_0 - LM Studio
lms get ggml-org/GLM-4.5V-GGUF@q8_0 - llama.cpp
llama-server -hf ggml-org/GLM-4.5V-GGUF:Q8_0
- Ollama
Notes
MoE model built on GLM-4.5-Air (106B total, 12B active); needs transformers>=4.57.1, sglang>=0.5.3 or vllm>=0.10.2, and the example serve commands use 4-way tensor parallelism. Thinking mode is on by default, and the card says pure-text Q&A is weaker because this release focused on multimodal use.
Questions
- How much VRAM does GLM 4.5V need?
- At Q4_K_M, GLM 4.5V needs about 61 GB of memory at 8k context and 61 GB at 8k, counting the weights, the KV cache and runtime buffers.
- What is the best GPU for running GLM 4.5V locally?
- The cheapest hardware in the US that runs GLM 4.5V fully in memory at 8k context is the Mac Studio M3 Ultra 96GB, $4,399 at eBay, at about 32 tok/s (estimated). The best value is the NVIDIA RTX PRO 6000 Blackwell (about 67 tok/s for $7,997). The fastest we price is the NVIDIA RTX PRO 6000 Blackwell, at about 67 tok/s.
- Can I run GLM 4.5V on a 16 GB GPU?
- No: it does not fit in 16 GB at 8k context, even with system RAM.
- Can I run GLM 4.5V on a 24 GB GPU?
- No: it does not fit in 24 GB at 8k context, even with system RAM.
- How do I run GLM 4.5V locally?
- With Ollama: ollama run hf.co/ggml-org/GLM-4.5V-GGUF:Q4_K_M (the Q4_K_M build). LM Studio and llama.cpp commands are on this page.
- What licence is GLM 4.5V released under?
- MIT, which allows commercial use.