Can the Apple M3 Ultra (512 GB) run Nex-N2.6?
Nex-N2.6·321B (18.3B active)·Apple M3 Ultra (512 GB)·512 GB unified memory
Yes. The Apple M3 Ultra (512 GB) runs Nex-N2.6 fully in unified memory at Q8_0 (about 357 GB of 384 GB), at roughly 23 tokens/s.
- best quant
- Q8_0
- needs
- 357 GB
- usable
- 384 GB
- est. speed
- ~23 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Nex-N2.6 page →
Every quantisation of Nex-N2.6 on the Apple M3 Ultra (512 GB)
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 146 GB | fits | ~75 tok/s |
| Q3_K_M | 175 GB | fits | ~50 tok/s |
| Q4_K_M | 219 GB | fits | ~41 tok/s |
| Q5_K_M | 261 GB | fits | ~35 tok/s |
| Q6_K | 298 GB | fits | ~30 tok/s |
| Q8_0 pick | 357 GB | fits | ~23 tok/s |
| FP16 / BF16 | 651 GB | too big | — |
Speed is a bandwidth-based estimate for generating text (819 GB/s); prompt processing and long contexts are slower.
Measured speed on the Apple M3 Ultra (512 GB)
No community reports for this pair yet.
Report your own speed →Run Nex-N2.6 on the Apple M3 Ultra (512 GB)
Using Q8_0, the best fit for Apple M3 Ultra (512 GB).
ollama run hf.co/bartowski/Nex-N2.6-GGUF:Q8_0 llama-server -hf bartowski/Nex-N2.6-GGUF:Q8_0brew install llama.cpp ships with Metal. Downloads the GGUF on first run.
lms get bartowski/Nex-N2.6-GGUF@Q8_0Then load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="nex-agi/Nex-N2.6", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Vision models that fit the Apple M3 Ultra (512 GB) comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 321BA18.3B | Q8_0 | ≈356 GBFits in memory | ~23 tok/s | |
| 180BA61.6B | Q8_0 | ≈185 GBFits in memory | ~6.9 tok/s | |
| 427B | Q6_K | ≈345 GBFits in memory | ~1.3 tok/s | |
| 220B | Q8_0 | ≈3.5 GBFits in memory | ~1.9 tok/s | |
| 383B | Q6_K | ≈311 GBFits in memory | ~1.4 tok/s | |
| 266BA1.7B | Q8_0 | ≈276 GBFits in memory | ~247 tok/s |
Frequently asked questions
- Can the Apple M3 Ultra (512 GB) run Nex-N2.6?
- Yes. The Apple M3 Ultra (512 GB) runs Nex-N2.6 fully in unified memory at Q8_0 (about 357 GB of 384 GB), at roughly 23 tokens/s.
- How fast does Nex-N2.6 run on the Apple M3 Ultra (512 GB)?
- An estimate from memory bandwidth gives about 23 tokens/s at Q8_0.
- Which quantisation of Nex-N2.6 should I use on the Apple M3 Ultra (512 GB)?
- Q8_0: the largest one that fits. Expected quality: lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.