Check my GPU

on

Can the NVIDIA GeForce RTX 3090 run Ornith 1.5 35B-A3B?

92 ptsExcellent (S) · 92 of 100 points: Model quality 38.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15

Yes, with little memory to spare

Tight fit. At Q4_K_M it needs about 23.9 GB of 24.0 GB usable, with an estimated speed of 191 tok/s.

Best quant
Q4_K_M
Generation speed
191 tok/s
Prompt processing
8,544 tok/s
First token (1K prompt)
0.3 s
Largest safe context
12K

Download Ornith 1.5 35B-A3B

Recommended for the NVIDIA GeForce RTX 3090: 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/ornith-ai/Ornith-1.5-35B-A3B-GGUF (opens in a new tab)

ollama run hf.co/ornith-ai/Ornith-1.5-35B-A3B-GGUF:Q4_K_M

Original weights · Hugging Face

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

huggingface.co/ornith-ai/Ornith-1.5-35B-A3B (opens in a new tab)

No sign-in needed.

Links checked 5 days 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.38.5 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.24.0 / 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.15.0 / 15
Total92.5 / 10092 ptsExcellent (S) · 92 of 100 points: Model quality 38.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15

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

Every quantization on the NVIDIA GeForce RTX 3090

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 16.3 GB 24.0 GB 314 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 28.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF files (opens in a new tab)
Q3_K_M 19.6 GB 24.0 GB 248 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 34.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF files (opens in a new tab)
Q4_K_M 23.9 GB 24.0 GB 191 tok/s Tight fit 92 ptsExcellent (S) · 92 of 100 points: Model quality 38.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q5_K_M 27.5 GB 24.0 GB 56.8 tok/s Runs with offload 79 ptsGreat (A) · 79 of 100 points: Model quality 39.3/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q6_K 31.4 GB 24.0 GB 30.9 tok/s Runs with offload 78 ptsGreat (A) · 78 of 100 points: Model quality 40.1/45, Memory fit 10.0/25, Speed 13.2/15, Memory use 15.0/15 GGUF (opens in a new tab)
Q8_0 40.1 GB 24.0 GB 15.0 tok/s Heavy offload 68 ptsGood (B) · 68 of 100 points: Model quality 40.5/45, Memory fit 4.0/25, Speed 9.2/15, Memory use 15.0/15 GGUF (opens in a new tab)
F16 73.9 GB 24.0 GB — Won't run 12 ptsWon't run (F) · 12 of 100 points: Model quality 12.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 GGUF (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.