Can the Radeon RX 7900 XTX run Llama 4 Scout (17B x 16E) Instruct?
Does not fit at Q4_K_M.
Llama 4 Scout (17B x 16E) Instruct is 109B parameters (MoE; all experts resident). At Q4_K_M the weights are about 60.9 GiB; with the 1.5 GiB runtime reserve that is 62.4 GiB against the card's 24GB, about 38.4 GiB more than the card has.
All three quants
24GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 60.9 GiB | 62.4 GiB | Does not fit | short 38.4 GiB |
| Q8_0near-lossless | 107.6 GiB | 109.1 GiB | Does not fit | short 85.1 GiB |
| FP16full weights | 203.0 GiB | 204.5 GiB | Does not fit | short 180.5 GiB |
Verdict rules: fits comfortably when weights plus reserve sit within 85% of VRAM; tight when they fit with little left for context; CPU offload when they exceed VRAM by up to 2x (runs, slowly, with layers in system RAM); no beyond that. The KV cache per token depends on the model's architecture and is not modelled here.
Not this card. These fit it comfortably at Q4.
Nothing in the consumer catalog fits Llama 4 Scout (17B x 16E) Instruct at Q4 on a single card; this is multi-GPU or datacenter territory, or a job for hosted inference (see PicksByModel for per-token pricing).
What the Radeon RX 7900 XTX does run well → · Llama 4 Scout (17B x 16E) Instruct on every card →
About the model
Llama 4 Scout (17B x 16E) Instruct by Meta: 10,485,760-token native context, text + vision, released 2025 under the Llama 4 Community License. Model card → · Hosted pricing on PicksByModel →