Check my GPU

on

Can the NVIDIA H100 NVL run Fara 1.5 27B?

94 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.9/15

Yes, it runs well

Runs well. At F16 it needs about 60.6 GB of 94.0 GB usable, with an estimated speed of 41.1 tok/s.

Best quant
F16
Generation speed
41.1 tok/s
Prompt processing
3,158 tok/s
First token (1K prompt)
0.3 s
Largest safe context
256K

Download Fara 1.5 27B

Recommended for the NVIDIA H100 NVL: F16. 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 F16 files (opens in a new tab)

huggingface.co/bartowski/Fara1.5-27B-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Fara1.5-27B-GGUF

Original weights · Hugging Face

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

huggingface.co/microsoft/Fara1.5-27B (opens in a new tab)

No sign-in needed.

Links checked 7 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.39.6 / 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.14.9 / 15
Total94.5 / 10094 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.9/15

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

Every quantization on the NVIDIA H100 NVL

Quant Memory needed Available Speed Fit Grade · points Download
Q2_K 16.8 GB 94.0 GB 287 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 27.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15 GGUF (opens in a new tab)
Q3_K_M 19.2 GB 94.0 GB 226 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15 GGUF (opens in a new tab)
Q4_K_M 22.5 GB 94.0 GB 175 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 GGUF (opens in a new tab)
Q5_K_M 25.3 GB 94.0 GB 145 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 38.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15 GGUF (opens in a new tab)
Q6_K 28.3 GB 94.0 GB 121 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 39.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 GGUF (opens in a new tab)
Q8_0 34.8 GB 94.0 GB 89.1 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 GGUF (opens in a new tab)
F16 60.6 GB 94.0 GB 41.1 tok/s Runs well 94 ptsExcellent (S) · 94 of 100 points: Model quality 39.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.9/15 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.