RTX A4000 for local LLMs
3 measured results from 2 builds, each linked to its source.
| Memory | 16 GB per card |
|---|---|
| Memory bandwidth | not listed |
| Typical EU price | ≈€1,050 new (PNY RTX A4000 16 GB GDDR6 VCNRTXA4000-PB, billiger.de, 2026-10-24) |
Can it run? Muse Glimmer 30B on RTX A4000 gpt-oss 20B on RTX A4000
All builds with the RTX A4000
| Build | GPU(s) | Memory GB (total) | Results |
|---|---|---|---|
| Intel Core Ultra 265K + RTX A4000 | RTX A4000 | 16 | 2 |
| RTX A4000 16GB (llm-speed signed run, Oct 2026): Muse Glimmer 30B UD-IQ3_XXS at 21.4 tok/s | RTX A4000 | 16 | 1 |
All measured results
(MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)
| Model | Build | Ran on | Quant | Engine | tok/s | Details |
|---|---|---|---|---|---|---|
| Muse Glimmer 30B | RTX A4000 16GB (llm-speed signed run, Oct 2026): Muse Glimmer 30B UD-IQ3_XXS at 21.4 tok/s | RTX A4000 | UD-IQ3_XXS | llama.cpp 0.7.0-dev (build 11803) | 21.42 | |
| gpt-oss 20B | Intel Core Ultra 265K + RTX A4000 | RTX A4000 | llama.cpp | 93.55 | ||
| Llama 3.2 3B legacy | Intel Core Ultra 265K + RTX A4000 | RTX A4000 | llama.cpp | 149.44 |
All RTX A4000 builds: see also all GPUs · best LLMs by memory size · download the dataset.
FAQ
How fast is the RTX A4000 for local LLMs?
The fastest plain-decode result we have is 149.44 tok/s on Llama 3.2 3B (, llama.cpp) in Intel Core Ultra 265K + RTX A4000. Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 3 measured results from 2 builds.
How much memory does the RTX A4000 have?
16 GB per card.
Which models have been measured on the RTX A4000?
Llama 3.2 3B, Muse Glimmer 30B, gpt-oss 20B.
Where do these numbers come from?
Every row links to a build page with its original public source (benchmark logs, READMEs, forum posts). RigBase does not re-run the benchmarks. Results marked ⚡ use speculative decoding and are not comparable 1:1 with plain decode.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.