Best home rig for GLM 4.7 Flash
Will it fit my GPU? Best value GPU per euro →
Real, measured generation speeds for GLM 4.7 Flash on home hardware, fastest first. Different quants/engines aren't directly comparable.
| Build | Quant | Engine | tok/s | Cost | |
|---|---|---|---|---|---|
| RTX 4090 (llm-speed signed runs, Oct 2026): Qwen3.6 35B-A3B 161 tok/s, Gemma 4 12B QAT 98 tok/s | Q4_K_M (EPYC 75F3 host) | Ollama 0.31.1 | 164.9 | source | |
| RTX 3090 (llm-speed signed runs, Oct 2026): gpt-oss 20B 207 tok/s, Qwen3.6 27B 43 tok/s | Q4_K_M (Threadripper PRO host) | Ollama 0.31.1 | 134.6 | source | |
| Microsoft Surface Laptop Ultra (RTX Spark N1X): llama.cpp speeds on 2026 models (Micro Center) | general, short prompt | llama.cpp (Nvidia ARM64 build) | 55.6 | source |
Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)
FAQ
What is the fastest measured hardware for GLM 4.7 Flash?
RTX 4090: 164.9 tok/s generation (Ollama 0.31.1, Q4_K_M (EPYC 75F3 host)), from https://llm-speed.com/r/r_m6j1zxwvp-f.
Which GPUs have measured results for GLM 4.7 Flash?
RTX 3090, RTX 4090, RTX Spark N1X.
Can it run on… RTX 3090 · RTX 4090 · RTX Spark N1X
Related: what GPU do you need for 2026 models · all builds