Can the Radeon RX 7900 XTX run GLM-4.7-Flash?
Fits comfortably at Q4_K_M.
GLM-4.7-Flash is 30B parameters (MoE; all experts resident). At Q4_K_M the weights are about 16.8 GiB; with the 1.5 GiB runtime reserve that is 18.3 GiB against the card's 24GB, leaving about 5.7 GiB for context.
All three quants
24GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 16.8 GiB | 18.3 GiB | Fits comfortably | 5.7 GiB |
| Q8_0near-lossless | 29.6 GiB | 31.1 GiB | Only with CPU offload | short 7.1 GiB |
| FP16full weights | 55.9 GiB | 57.4 GiB | Does not fit | short 33.4 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.
The numbers for this pairing
At Q4_K_M the weights take about 16.8 GiB; with the 1.5 GiB we set aside for the runtime that is 18.3 of the card's 24 GB, leaving about 5.7 GB for the context cache.
It is a mixture-of-experts model: about 3B of its 30B parameters work on each token, which helps speed, but all of them still have to fit in memory.
This is the cheapest card on our list that runs it comfortably at Q4, at about $850.
At about $850, this card costs roughly $35 per GB of VRAM.
Running it at its full 355 W board power for 4 hours a day would use about 43 kWh a month, about $7.84 at the US average residential rate of 18.4 cents per kWh (2026-05); real use sits below that ceiling.
Prices are the lowest current listings our tracker saw on Oct 7, 2026, since averages include premium variants; launch prices are marked where we have no listing.
Good match. Get the card.
The Radeon RX 7900 XTX clears GLM-4.7-Flash at Q4_K_M. Live listings below; this page was rebuilt 2026-10-07.
Amazon links may earn us a commission. Prices move daily; the links open live listings.
About the model
GLM-4.7-Flash by Z.ai (Zhipu): 202,752-token native context, text, released 2026 under the MIT. Model card → · Hosted pricing on PicksByModel →