Apertus 70B Instruct on AMD Radeon RX 9070

Can the AMD Radeon RX 9070 run Apertus 70B Instruct?

Yes, but slowly (heavy RAM offload)

Slow (heavy RAM offload). At Q2_K it needs about 32.3 GB of 16.0 GB usable, with an estimated speed of 3.0 tok/s.

Best quant: Q2_K
Generation speed: 3.0 tok/s
Prompt processing: 378 tok/s
First token (1K prompt): 2.7 s
Largest safe context: —

Best app to run it on the AMD Radeon RX 9070

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Usually the first to support new model architectures.

llama-server -hf unsloth/Apertus-70B-Instruct-2509-GGUF:Q2_K

LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
Lemonade Splits the model between GPU memory and system RAM, which this setup needs.

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Usually the first to support new model architectures.

llama-server -hf unsloth/Apertus-70B-Instruct-2509-GGUF:Q2_K

LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
Lemonade Splits the model between GPU memory and system RAM, which this setup needs.

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 AMD Radeon RX 9070: Q2_K. 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 Q2_K 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:Q2_K

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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_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 Slowheavy RAM offload: How well it runs on the AMD Radeon RX 9070: 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.	18.9 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	4.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	4.1 / 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 score	42.0 / 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 AMD Radeon RX 9070

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	32.3 GB	16.0 GB	3.0 tok/s	Slowheavy RAM offload	42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	38.7 GB	16.0 GB	—	Won't run	50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	47.2 GB	16.0 GB	—	Won't run	57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	54.2 GB	16.0 GB	—	Won't run	58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	62.0 GB	16.0 GB	—	Won't run	59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	78.9 GB	16.0 GB	—	Won't run	60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	145 GB	16.0 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

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. NVIDIA RTX PRO 6000 Blackwell Q4_K_M · 31.2 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 69/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q3_K_M · 10.6 tok/s · Runs well (tight fit)
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q4_K_M · 12.0 tok/s · Runs well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q4_K_M · 12.3 tok/s · Runs well
50Fair quality (C) · 50 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. Apple M4 Max (128 GB) Q3_K_M · 10.6 tok/s · Runs well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 12.3 tok/s · Runs well

Quick answers

How much memory does Apertus 70B Instruct need on the RX 9070 16GB?

At Q2_K it needs about 32.3 GB. The RX 9070 16GB has 16.0 GB usable.

How fast is Apertus 70B Instruct on the RX 9070 16GB?

About 3.0 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Apertus 70B Instruct should I use on the RX 9070 16GB?

Q2_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.