on

Can the AMD Instinct MI350X run Prometheus 2 8x7B?

73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.

Yes, but slowly

Slow. At Q6_K it needs about 53.6 GB of 288 GB usable and makes one decision in about 819 ms.

Best quant
Q6_K
Time per decision
819 ms
Decisions per second
1.2/s
Input assumed
1,024 tokens
Returns
Written feedback, then a score

Best app to run it on the AMD Instinct MI350X

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 prometheus-eval/prometheus-8x7b-v2.0
  • Lemonade AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
  • LM Studio Point-and-click: search, download and chat in one window.

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

  • AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
lemonade pull mradermacher/prometheus-8x7b-v2.0-GGUF:Q6_K
  • 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 Prometheus 2 8x7B

Recommended for the AMD Instinct MI350X: Q6_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 Q6_K file (opens in a new tab)

huggingface.co/mradermacher/prometheus-8x7b-v2.0-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/prometheus-8x7b-v2.0-GGUF:Q6_K

Original weights · Hugging Face

Full-precision files from Prometheus Eval, for fine-tuning, vLLM, Transformers.

huggingface.co/prometheus-eval/prometheus-8x7b-v2.0 (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 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (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: S 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Slow
How well it runs on the AMD Instinct MI350X: 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.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.33.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.5.2 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.9.0 / 15
Match score72.2 / 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 AMD Instinct MI350X

Quant Memory needed Available Time per decision Runs Quality Download
Q4_K_M 43.8 GB 288 GB 617 ms Slow 70Great quality (A) · 70 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. GGUF (opens in a new tab)
Q5_K_M 48.4 GB 288 GB 713 ms Slow 71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 53.6 GB 288 GB 819 ms Slow 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 64.8 GB 288 GB 1.1 s Slow 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 109 GB 288 GB 2.1 s Very slow 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Times are for one request with a 1,024-token input and about 150 tokens written. Batching servers process many requests at once.

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.