Builds / RTX 4070 12GB
RTX 4070 12 GB running Mellum 2.1 12B-A2.5B Thinking Q4_K_M
Source: llm-bench.io ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
- GPU(s)
- RTX 4070 12GB
Amazon · eBay (used) · Newegg - VRAM / unified memory (GB)
- 12
- CPU
- not stated
- Motherboard
- not stated
- RAM
- not stated
- PSU
- not stated
- Other
- not stated
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| Mellum 2.1 12B-A2.5B | Thinking GGUF Q4_K_M | llama.cpp | 177.5 | prefill 1,161.2 tok/scontext: 131K📏 llm-bench.io submission (2026-10-13), memory 8.9 GB |
llm-bench.io community submission. Rest of the system not stated.
Source: https://llm-bench.io/benchmarks/cmv76txyv004p01m4h40td1d6
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
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)