Home / Models / GLM-4-9B-0414 / NVIDIA GTX 1660 Ti 6 GB

Calculated memory fit · not a benchmark

Can GLM-4-9B-0414 run on NVIDIA GTX 1660 Ti 6 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-4-9B-0414 · 9.4B
GPU
NVIDIA GTX 1660 Ti 6 GB · 6 GB advertised

Memory calculation

Breakdown for Q4 at 8K context, batch size 1. Calculator v1.0.0.

Model weights5.5 GB
KV cache0.3 GB
Runtime reserve0.8 GB
Safety margin0.4 GB
Required (estimated)7.0 GB
GPU usable VRAM5.4 GB

Result: CPU RAM OFFLOAD REQUIRED

Quantization table

Quantization2K4K8K16K32K
BF16NoNoNoNoNo
FP16NoNoNoNoNo
Q3OffloadOffloadOffloadOffloadOffload
Q4OffloadOffloadOffloadOffloadOffload
Q5OffloadOffloadOffloadOffloadOffload
Q6OffloadOffloadOffloadOffloadOffload
Q8OffloadOffloadOffloadOffloadOffload

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. RigForAI does not estimate tokens/sec in this release.

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.

Check price on Amazon

GIGABYTE

GIGABYTE GAMING GeForce GTX 1660 Ti OC 6G

6 GB · Amazon unmatched

Check availability
MSI

MSI ARMOR GeForce GTX 1660 Ti 6G OC

6 GB · Amazon unmatched

Check availability
MSI

MSI VENTUS GeForce GTX 1660 Ti XS 6G OC

6 GB · Amazon unmatched

Check availability
GIGABYTE

GIGABYTE GeForce GTX 1660 Ti MINI ITX OC 6G

6 GB · Amazon unmatched

Check availability
MSI

MSI GAMING GeForce GTX 1660 Ti X 6G

6 GB · Amazon unmatched

Check availability
GIGABYTE

GIGABYTE AORUS GeForce GTX 1660 Ti 6G

6 GB · Amazon unmatched

Check availability

Sources

Model: official config THUDM/GLM-4-9B-0414 (main). GPU/product specs: Icecat. Compatibility: RigForAI calculator v1.0.0 estimated VRAM · Q8 at 8K: CPU_RAM_OFFLOAD_REQUIRED. Amazon: affiliate commerce match, not a spec source.