Home / Models / GLM-4.5 Air / NVIDIA RTX 3090 24 GB
Can GLM-4.5 Air run on NVIDIA RTX 3090 24 GB?
Can it run? Yes, with CPU/RAM offload. Full GPU fit? No.
Can it run?
- Can it run?
- Yes, with CPU/RAM offload. This is not equivalent to full-GPU inference.
- Full GPU fit?
- No
- Model
- GLM-4.5 Air · 110B
- GPU
- NVIDIA RTX 3090 24 GB · 24 GB advertised
What else can NVIDIA RTX 3090 24 GB run? · Find other GPUs for GLM-4.5 Air · See 2× multi-GPU options
Memory calculation
Breakdown for Q4 at 8K context, batch size 1. Calculator v1.0.0.
| Model weights | 64.8 GB |
|---|---|
| KV cache | 1.4 GB |
| Runtime reserve | 3.7 GB |
| Safety margin | 2.2 GB |
| Required (estimated) | 72.2 GB |
| GPU usable VRAM | 21.6 GB |
Result: DOES NOT FIT
Quantization table
| Quantization | 2K | 4K | 8K | 16K | 32K | 64K | 128K |
|---|---|---|---|---|---|---|---|
| BF16 | No | No | No | No | No | No | No |
| FP16 | No | No | No | No | No | No | No |
| Q3 | Offload | Offload | Offload | Offload | Offload | Offload | Offload |
| Q4 | No | No | No | No | No | No | No |
| Q5 | No | No | No | No | No | No | No |
| Q6 | No | No | No | No | No | No | No |
| Q8 | No | No | No | No | No | No | No |
What fits entirely in VRAM?
No calculated full-VRAM fit at the evaluated quantizations and context lengths.
What requires RAM offload?
Weights may run with CPU/RAM offload. That is not equivalent to full-GPU inference. Performance numbers below are only published for full-VRAM fits.
Performance
No llama.cpp performance result is published for this pair yet. Memory fit above is unchanged. How performance is calculated
Available graphics cards
These SKUs use this GPU chip. Amazon CTAs appear only for EXACT/HIGH matches. Absence of a price does not change the compatibility result above.
GIGABYTE GV-N3090TURBO-24GD graphics card NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon EXACT
$1995.00
Check price on Amazon
MSI GAMING RTX 3090 X TRIO 24G graphics card NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon EXACT
$2069.00
Check price on Amazon
GIGABYTE GAMING GV-N3090GAMING OC-24GD graphics card NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon EXACT
$1989.00
Check price on Amazon
MSI VENTUS GeForce RTX 3090 3X 24G OC NVIDIA 24 GB GDDR6X
24 GB · Amazon EXACT
$1995.00
Check price on Amazon
GIGABYTE AORUS GV-N3090AORUS M-24GD graphics card NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon EXACT
$1899.00
Check price on Amazon
GIGABYTE AORUS GeForce RTX 3090 XTREME WATERFORCE 24G NVIDIA 24 GB GDDR6X
24 GB · Amazon EXACT
$2389.00
Check price on Amazon
GIGABYTE EAGLE GV-N3090EAGLE OC-24GD graphics card NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon EXACT
$1347.22
Check price on Amazon
GIGABYTE AORUS GV-N3090AORUS X-24GD graphics card NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon EXACT
$1462.22
Check price on Amazon
ASUS TUF Gaming TUF-RTX3090-O24G-GAMING graphics card NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon EXACT
Check price on Amazon
ASUS TUF Gaming TUF-RTX3090-O24G-GAMING NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon unmatched
ASUS ROG -STRIX-RTX3090-O24G-WHITE NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon unmatched
ASUS ROG -STRIX-RTX3090-24G-GAMING NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon unmatched
ASUS TUF Gaming TUF-RTX3090-24G-GAMING NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon unmatched
GIGABYTE GAMING RTX 3090 BOX NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon unmatched
ASUS Turbo -RTX3090-24G NVIDIA GeForce RTX 3090 24 GB GDDR6X
24 GB · Amazon unmatched
Sources
Model: official config zai-org/GLM-4.5-Air (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 8K: DOES_NOT_FIT. Amazon: affiliate commerce match, not a spec source.