Can an RTX 4090 run glm-4.7-flash?
Yes: an RTX 4090 runs glm-4.7-flash 29.9B at 164.9 tok/s at Q4_K_M, measured on ollama with a 105-token prompt in October 2026.
2 signed runs on llm-speed. Single-request decode speed in tokens per second; the short-chat workload unless noted. 1 of 2 runs were measured by llm-speed (@llmspeed); the other one is community-submitted (signed on the submitter's own machine, not measured by llm-speed, and not used for llm-speed verdicts). Runs measured by llm-speed are credited to @llmspeed. Verdicts and headline numbers use only llm-speed's own runs and fit tests.
Measured tok/s by quant and runtime
| Quant | Runtime | Build | Decode tok/s (best run) | Workload | Runs | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | ollama | 0.31.1 | 164.9 | chat-short | 1 | Measured by llm-speed@llmspeed |
| Q4_K_M | ollama | 0.31.1 | 129.9 | agent-trace | 1 | Community-submitted |
Fastest quant that fits: Q4_K_M on ollama, 164.9 tok/s (measured by llm-speed; it fits because it ran on this hardware). Quants without a run are not listed.
Every measured row
| Run | Date (UTC) | Workload | Quant | Runtime / build | Prompt tokens | Output tokens | Decode tok/s | Prefill tok/s | TTFT ms | VRAM GiB | Source |
|---|---|---|---|---|---|---|---|---|---|---|---|
| r_ted0u8uyre0 | 2026-10-16 | chat-short | Q4_K_M | ollama · 0.31.1 | 105 | 256 | 164.9 | 3.7 | 28106 | – | Measured by llm-speed@llmspeed |
| r_ted0u8uyre0 | 2026-10-16 | chat-long | Q4_K_M | ollama · 0.31.1 | 3132 | 1024 | 146.1 | 3617.7 | 866 | – | Measured by llm-speed@llmspeed |
| r_ted0u8uyre0 | 2026-10-16 | agent-trace | Q4_K_M | ollama · 0.31.1 | 3145 | 840 | 155.5 | 3224.6 | 641 | – | Measured by llm-speed@llmspeed |
| r_o636l3cc-rr | 2026-07-08 | agent-trace | Q4_K_M | ollama · 0.31.1 | 3145 | 840 | 129.9 | 2491.1 | 1262 | – | Community-submitted |
| r_ted0u8uyre0 | 2026-10-16 | concurrent-decode | Q4_K_M | ollama · 0.31.1 | 1024 | 256 | 155.2 | – | – | – | Measured by llm-speed@llmspeed |
Questions
Can an RTX 4090 run glm-4.7-flash?
Yes: an RTX 4090 runs glm-4.7-flash 29.9B at 164.9 tok/s at Q4_K_M, measured on ollama with a 105-token prompt in October 2026.
How many tokens per second does glm-4.7-flash get on an RTX 4090?
Decode speed measured by llm-speed, by quantization and runtime: Q4_K_M on ollama: 164.9 tok/s. Based on 1 run measured by llm-speed; single-request chat-short unless noted. 1 community-submitted run is listed on the page, labelled, and not counted here.
What is the fastest quant of glm-4.7-flash that fits on an RTX 4090?
Q4_K_M on ollama was the fastest measured setting at 164.9 tok/s; it fit because it ran. Other quants are listed only where a run measured them.
How much VRAM does glm-4.7-flash use on an RTX 4090?
Memory use was not recorded for these runs. The VRAM calculator gives an estimate, not a measurement.