on

Can the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) run Apertus v1.5 70B?

65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.

Yes, but slowly

Slow. At Q6_K it needs about 70.5 GB of 102 GB usable, with an estimated speed of 3.5 tok/s.

Best quant
Q6_K
Generation speed
3.5 tok/s
Prompt processing
288 tok/s
First token (1K prompt)
3.6 s
Largest safe context
102K

Best app to run it on the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)

On Linux

vLLM

Inference server · runs on vLLM

  • The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
vllm serve swiss-ai/Apertus-v1.5-70B
  • SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
  • Docker Model Runner Handy if you already work in Docker.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Apertus v1.5 70B

Original weights · Hugging Face

Full-precision files from Swiss AI, for fine-tuning, vLLM, Transformers.

huggingface.co/swiss-ai/Apertus-v1.5-70B (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q6_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Slow
How well it runs on the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.29.4 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.4.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.15.0 / 15
Match score73.9 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 40.3 GB 102 GB 8.4 tok/s Slow 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q3_K_M 46.8 GB 102 GB 6.6 tok/s Slow 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q4_K_M 55.4 GB 102 GB 5.1 tok/s Slow 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q5_K_M 62.6 GB 102 GB 4.2 tok/s Slow 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 70.5 GB 102 GB 3.5 tok/s Slow 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 87.8 GB 102 GB 2.6 tok/s Very slowtight fit 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 155 GB 102 GB — Won't run 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?