Home / Multi-GPU

llama.cpp · homogeneous 2–4 GPUs · not a PC builder

Can this model run across multiple GPUs?

Phase 8 answers memory feasibility for identical cards under llama.cpp. Default split is layer (pipeline parallel: each GPU owns a slice of layers; KV stays with those layers). This is not 2 × VRAM = pool, and it is not a complete PC build.

2× AMD Radeon RX 7900 XTX 24 GB

Does not fit on this configuration

Model
GLM-4.5 · Q4 · 8K
Runtime / split
llama.cpp · layer · calculator 1.0.0
Single-GPU status
DOES_NOT_FIT · required 230.7 GB vs usable 21.6 GB
Per card advertised / usable
24 GB / 21.6 GB
Aggregate advertised
48.0 GB — capacity, not effective model capacity
Nominal aggregate usable
43.2 GB (N × advertised × 0.90)
Effective per-GPU peak
115.7 GB vs usable 21.6 GB
Per-GPU split (approx.)
weights 105.1 GB · KV 1.4 GB · runtime 5.8 GB · safety 3.4 GB
Why
Even a 2K context exceeds per-GPU usable VRAM after partition and per-device reserves.
Topology
Requires space for 2 discrete GPUs. Exact cooler slot width is not in the RigForAI graph. layer split is pipeline parallel and can run over PCIe. KV stays with the layers on each GPU. NVLink is not treated as a 1× aggregate VRAM pool.
Performance
Phase 5 predictions are single-GPU. Multi-GPU tok/s is not published.
GPU-only current cost
$2119.98 = 2 × $1059.99 at the current per-card matched price. This does not mean 2 units are in stock, and it is not a complete build cost.
GIGABYTE GAMING Radeon RX 7900 XTX OC 24G AMD 24 GB GDDR6 · ASIN B0BRBXF3MW
Amazon
Formula
per_gpu_peak = ceil(weight_bytes/N) + ceil(kv_bytes/N) + runtime_base + safety_base + weight_fractions×ceil(weight_bytes/N). Compare to usable = advertised×0.90. Not (single_gpu_required × N) and not advertised_vram × N as effective capacity.

AMD Radeon RX 7900 XTX 24 GB · Single-GPU can-run · Find a single GPU · Build a machine for this GPU setup

Query combinations are not indexed. Source: llama.cpp multi-GPU documentation.