Can an RTX 4090 run 3.1-8B-Instruct?
Yes: an RTX 4090 runs 3.1 8B at 160.8 tok/s at Q4_K_M, measured on llama.cpp with a 135-token prompt in October 2026.
1 signed run on llm-speed. Single-request decode speed in tokens per second; the short-chat workload unless noted. This run was measured by llm-speed (@llmspeed). Runs measured by llm-speed are credited to @llmspeed.
Measured tok/s by quant and runtime
| Quant | Runtime | Build | Decode tok/s (best run) | Workload | Runs | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | llama.cpp | commit a37cc4610 | 160.8 | chat-short | 1 | Measured by llm-speed@llmspeed |
Fastest quant that fits: Q4_K_M on llama.cpp, 160.8 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_32ipo1hbbwl | 2026-10-22 | chat-short | Q4_K_M | llama.cpp · commit a37cc4610 | 135 | 256 | 160.8 | 4283.1 | 32 | – | Measured by llm-speed@llmspeed |
Questions
Can an RTX 4090 run 3.1-8B-Instruct?
Yes: an RTX 4090 runs 3.1 8B at 160.8 tok/s at Q4_K_M, measured on llama.cpp with a 135-token prompt in October 2026.
How many tokens per second does 3.1-8B-Instruct get on an RTX 4090?
Decode speed measured by llm-speed, by quantization and runtime: Q4_K_M on llama.cpp: 160.8 tok/s. Based on 1 run measured by llm-speed; single-request chat-short unless noted.
What is the fastest quant of 3.1-8B-Instruct that fits on an RTX 4090?
Q4_K_M on llama.cpp was the fastest measured setting at 160.8 tok/s; it fit because it ran. Other quants are listed only where a run measured them.
How much VRAM does 3.1-8B-Instruct use on an RTX 4090?
Memory use was not recorded for these runs. The VRAM calculator gives an estimate, not a measurement.