on

Can the NVIDIA RTX PRO 6000 Blackwell run Apertus 70B Instruct?

57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q4_K_M it needs about 51.2 GB of 96.0 GB usable, with an estimated speed of 31.2 tok/s.

Best quant
Q4_K_M
Generation speed
31.2 tok/s
Prompt processing
1,275 tok/s
First token (1K prompt)
0.8 s
Largest safe context
64K

Best app to run it on the NVIDIA RTX PRO 6000 Blackwell

On Windows

LM Studio

Desktop app · runs on llama.cpp, MLX

  • Point-and-click: search, download and chat in one window.

Open Apertus 70B Instruct in LM Studio

  • llama.cpp Usually the first to support new model architectures.
  • Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

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-70B-Instruct-2509
  • LM Studio Point-and-click: search, download and chat in one window.
  • llama.cpp Usually the first to support new model architectures.

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 70B Instruct

Recommended for the NVIDIA RTX PRO 6000 Blackwell: Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M file (opens in a new tab)

huggingface.co/unsloth/Apertus-70B-Instruct-2509-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Apertus-70B-Instruct-2509-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/swiss-ai/Apertus-70B-Instruct-2509 (opens in a new tab)

No sign-in needed.

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q4_K_M, 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 Runs great
How well it runs on the NVIDIA RTX PRO 6000 Blackwell: 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.25.7 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.13.2 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.12.3 / 15
Match score76.2 / 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 PRO 6000 Blackwell

Quant Memory needed Available Speed Runs Quality Download
Q2_K 36.3 GB 96.0 GB 51.2 tok/s Runs great 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 42.7 GB 96.0 GB 40.3 tok/s Runs great 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 51.2 GB 96.0 GB 31.2 tok/s Runs great 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 58.2 GB 96.0 GB 25.7 tok/s Runs well 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q6_K 66.0 GB 96.0 GB 21.6 tok/s Runs well 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
Q8_0 82.9 GB 96.0 GB 15.9 tok/s Runs welltight fit 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. GGUF · folder (opens in a new tab)
F16 149 GB 96.0 GB — Won't run 60Good quality (B) · 60 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. GGUF · folder (opens in a new tab) 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?