llamaperf
Submit

Nemotron 3.5 Super

1 report

Nemotron 3.5 Super 120B · 12B active at 4-bit generates a median of 31.0 tokens per second on the AMD Strix Halo 128GB, the hardware it is most run on, from one plain run (community reports, as of 20 Oct 2026).

As of 20 Oct 2026, Nemotron 3.5 Super 120B · 12B active at 4-bit on the hardware it is most run on, with the median of plain runs (one device, one request, no speculative decoding, the whole model in its memory):

Nemotron 3.5 Super VRAM requirements by size and quant →

How does Nemotron 3.5 Super run on your hardware?

Pick your GPU or Mac, then read the speeds people reported for Nemotron 3.5 Super on it, or estimate memory fit and speed.

Buying hardware? Compare GPUs →

Free to use. No account needed. Memory estimates and community measurements are labelled separately.

Run Nemotron 3.5 Super yourself? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Benchmark with your agentPaste a result

Reported performance for Nemotron 3.5 Super

Filter this model’s reports by setup →
Thin page (1 of 3 reports needed for indexing). Add yours.
Tone: positiveAMD hardware
generation:
31.0 tokens/s
quant:
Q4_K_M (GGUF)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.

coding

User compares Nemotron 3.5 Super VL 120B-A12B at 31 t/s against Qwen 3.8 27B at 15 t/s on an AMD Strix Halo 128GB. Setup is LM Studio on Windows 11, with the Nemotron in Q4_K_M and the Qwen in Q8_0. Both models were asked to write a single canvas HTML animation explaining noise cancelling headphones; the user says the Nemotron result is clearly better and hits above its weight class. Nemotron thought for 7 minutes, Qwen for 20.

Oct 20, 2026

Get a weekly email of new Nemotron 3.5 Super reports on any GPU.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardwareQuant / engineReported contextGeneration
Nemotron 3.5 Super 120B (12B active) VL
AMD Strix Halo 128GB
Q4_K_M
LM Studio
Not reported31.0 tokens/s

Frequently asked

What hardware do people run Nemotron 3.5 Super on?

The hardware Nemotron 3.5 Super 120B · 12B active at 4-bit is most run on: AMD Strix Halo 128GB (31.0 t/s median, one run). Medians of plain runs, as of 20 Oct 2026.

Which inference engines do people use for Nemotron 3.5 Super?

Reports of Nemotron 3.5 Super name LM Studio (1 report), as of 20 Oct 2026.