Check my GPU

on

Can the NVIDIA RTX PRO 5000 Blackwell 72GB run Apodex 1.1 Mini (35B-A3B)?

93 ptsExcellent (S) · 93 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15

Yes, it runs well

Runs well. At Q8_0 it needs about 42.5 GB of 72.0 GB usable, with an estimated speed of 140 tok/s.

Best quant
Q8_0
Generation speed
140 tok/s
Prompt processing
15,600 tok/s
First token (1K prompt)
0.3 s
Largest safe context
256K

Download Apodex 1.1 Mini (35B-A3B)

Quantized files · GGUF

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

huggingface.co/apodex/Apodex-1.1-mini-GGUF (opens in a new tab)

ollama run hf.co/apodex/Apodex-1.1-mini-GGUF

Original weights · Hugging Face

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

huggingface.co/apodex/Apodex-1.1-mini (opens in a new tab)

No sign-in needed.

Links checked 5 hours ago against Hugging Face, Ollama and GitHub.

How the S grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.40.1 / 45
Memory fitFull marks when everything sits in GPU or unified 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.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.13.6 / 15
Total93.7 / 10093 ptsExcellent (S) · 93 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every quantization on the NVIDIA RTX PRO 5000 Blackwell 72GB

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 18.7 GB 72.0 GB 452 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15 GGUF files (opens in a new tab)
Q3_K_M 22.0 GB 72.0 GB 355 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 33.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15 GGUF files (opens in a new tab)
Q4_K_M 26.3 GB 72.0 GB 275 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.4/15 GGUF (opens in a new tab)
Q5_K_M 29.9 GB 72.0 GB 227 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 38.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.6/15 GGUF files (opens in a new tab)
Q6_K 33.8 GB 72.0 GB 191 tok/s Runs well 90 ptsExcellent (S) · 90 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.8/15 GGUF files (opens in a new tab)
Q8_0 42.5 GB 72.0 GB 140 tok/s Runs well 93 ptsExcellent (S) · 93 of 100 points: Model quality 40.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15 GGUF files (opens in a new tab)
F16 76.3 GB 72.0 GB 30.2 tok/s Runs with offload 78 ptsGreat (A) · 78 of 100 points: Model quality 40.1/45, Memory fit 10.0/25, Speed 13.0/15, Memory use 15.0/15 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.