Q4_K_M
177.5 GBMin VRAM: 204.1 GB
Recommended VRAM: 230.8 GB
Min RAM: 267 GB
Context: 8K / 8K
Loading model details...
Fetching variants, compatibility details, and metadata.
Loading model details...
Fetching variants, compatibility details, and metadata.
Share GLM 4.7 with someone who is deciding what to run locally.
Social proof
1% of 984 scanned PCs run GLM 4.7 fully on GPU.
206 keep at least some work on GPU. Based on anonymous compatibility checks.
General-purpose local model brief
Best for
Consider alternatives if
Quantization tip: Benchmark at least two quantizations and validate with a task-specific eval set before production use.
New to local models? Smaller quantization variants are easier to run, while larger ones can improve quality at the cost of more memory.
Q4_K_M
177.5 GBMin VRAM: 204.1 GB
Recommended VRAM: 230.8 GB
Min RAM: 267 GB
Context: 8K / 8K
Q5_K_M
221.9 GBMin VRAM: 255.2 GB
Recommended VRAM: 288.5 GB
Min RAM: 333 GB
Context: 8K / 8K
Q8_0
355 GBMin VRAM: 408.2 GB
Recommended VRAM: 461.5 GB
Min RAM: 533 GB
Context: 8K / 8K
FP16
710 GBMin VRAM: 816.5 GB
Recommended VRAM: 923 GB
Min RAM: 1065 GB
Context: 8K / 8K
| Quantization | File Size | Min VRAM | Recommended VRAM | Min RAM | Context |
|---|---|---|---|---|---|
| Q4_K_M | 177.5 GB | 204.1 GB | 230.8 GB | 267 GB | 8K / 8K |
| Q5_K_M | 221.9 GB | 255.2 GB | 288.5 GB | 333 GB | 8K / 8K |
| Q8_0 | 355 GB | 408.2 GB | 461.5 GB | 533 GB | 8K / 8K |
| FP16 | 710 GB | 816.5 GB | 923 GB | 1065 GB | 8K / 8K |
These GPUs meet the recommended 230.8 GB VRAM for the Q4_K_M quantization. Estimated speeds are approximate and assume full GPU offloading.
Budget Pick
Apple M4 Ultra256 GB VRAM · ~4.9 tok/s
Lowest cost that meets recommended VRAM
Check price on AmazonNeed a detailed comparison? See all GPU rankings for GLM 4.7.