Can I run Nemotron 3 Nano 30B-A3B on an RX 7900 XTX?
Yes: Nemotron 3 Nano 30B-A3B needs about 20.3 GB at Q4_K_M with 32K tokens of context, which fits the 24 GB RX 7900 XTX with 3.72 GB to spare. Nothing more precise fits at 32K with 0.5 GB to spare; Q4_K_M runs up to 256K (full) tokens on the RX 7900 XTX.
Yes Q4_K_M with 32K tokens of context
- Q4_K_M, 32K
- 20.3 GB
- RX 7900 XTX
- 24 GB, 960 GB/s
- To spare
- 3.72 GB
- Tokens/s
- 105–188 tokens/s
At Q4_K_M with 32K tokens of context it writes about 105–188 tokens/s for one request on an RX 7900 XTX.
Best precision for Nemotron 3 Nano 30B-A3B on an RX 7900 XTX
The most precise setting that leaves at least 0.5 GB free; one that fits with less is marked tight.
| Context | Best fit | Memory | Free | Tokens/s |
|---|---|---|---|---|
| 8K | Q5_K_M | 23.5 GB | 533 MB | 97–173 |
| 32K | Q4_K_M | 20.3 GB | 3.72 GB | 105–188 |
| 128K | Q4_K_M | 20.9 GB | 3.10 GB | 86–152 |
| 256K (full) | Q4_K_M | 21.7 GB | 2.28 GB | 69–121 |
Nemotron 3 Nano 30B-A3B on the RX 7900 XTX as the context fills
One request, FP16 KV cache, 0.5 GB plus 10% overhead; a minus sign is memory missing, and tight is less than 0.5 GB free.
| Context | Q4_K_M | Free | Tokens/s | Q8_0 | Free | Tokens/s |
|---|---|---|---|---|---|---|
| 4K | 20.1 GB | 3.90 GB | 112–201 | 34.9 GB | −10.9 GB | — |
| 8K | 20.1 GB | 3.88 GB | 111–199 | 34.9 GB | −10.9 GB | — |
| 16K | 20.2 GB | 3.83 GB | 109–195 | 35.0 GB | −11.0 GB | — |
| 32K | 20.3 GB | 3.72 GB | 105–188 | 35.1 GB | −11.1 GB | — |
| 64K | 20.5 GB | 3.52 GB | 98–174 | 35.3 GB | −11.3 GB | — |
| 128K | 20.9 GB | 3.10 GB | 86–152 | 35.7 GB | −11.7 GB | — |
| 256K (full) | 21.7 GB | 2.28 GB | 69–121 | 36.5 GB | −12.5 GB | — |
--n-cpu-moe for Nemotron 3 Nano 30B-A3B on the RX 7900 XTX
The measured Q4_K_M GGUF fits the RX 7900 XTX whole at 32K (23.8 GB), so --n-cpu-moe is not needed there. Measured Q4_K_M file, 1 GB of buffers; tokens/s by system RAM speed.
Nemotron 3 Nano 30B-A3B on more than one RX 7900 XTX
| Cards | Best at 32K | Tokens/s | Q4_K_M longest | Q4_K_M tokens/s |
|---|---|---|---|---|
| 2× (48 GB) | Q8_0 | 97–186 | 256K (full) | 133–269 |
| 4× (96 GB) | BF16 | 103–198 | 256K (full) | 181–399 |
Tensor parallel with the combined bandwidth, as in vLLM; llama.cpp splits layers by default and runs at about one card's speed.
Other options
- The next smaller setting, Q3_K_M, takes 16.5 GB at 32K, 7.48 GB under the RX 7900 XTX; it fits with 0.5 GB to spare up to 256K (full) tokens.
- Smallest setup for Q4_K_M at 32K: RTX 3090 (24 GB).
Run Nemotron 3 Nano 30B-A3B on the RX 7900 XTX with llama-server
llama-server -hf ggml-org/NVIDIA-Nemotron-3-Nano-30B-A3B-GGUF:Q4_K_M -c 4096NVIDIA-Nemotron-3-Nano-30B-A3B-Q4_K_M.gguf, 22.4 GB, from ggml-org/
Questions
Can I run Nemotron 3 Nano 30B-A3B on an RX 7900 XTX?
Yes: Nemotron 3 Nano 30B-A3B needs about 20.3 GB at Q4_K_M with 32K tokens of context, which fits the 24 GB RX 7900 XTX with 3.72 GB to spare. Nothing more precise fits at 32K with 0.5 GB to spare; Q4_K_M runs up to 256K (full) tokens on the RX 7900 XTX.
How fast is Nemotron 3 Nano 30B-A3B on an RX 7900 XTX?
At Q4_K_M with 32K tokens of context it writes about 105–188 tokens/s for one request on an RX 7900 XTX.
Does Nemotron 3 Nano 30B-A3B need --n-cpu-moe on an RX 7900 XTX?
The measured Q4_K_M GGUF fits the RX 7900 XTX whole at 32K (23.8 GB), so --n-cpu-moe is not needed there.
What does a second RX 7900 XTX change for Nemotron 3 Nano 30B-A3B?
Two RX 7900 XTX cards (48 GB in one tensor-parallel group) hold Nemotron 3 Nano 30B-A3B at Q8_0 with 32K, and Q4_K_M up to 256K (full) tokens, at about 133–269 tokens/s.
Try other settings in the VRAM calculator, the speed calculator or the MoE offload planner. See also Nemotron 3 Nano 30B-A3B VRAM requirements, what LLMs an RX 7900 XTX can run and every pair, or detect your own GPU. Model data checked .