Jamba 1.5 Large on Apple M3 Ultra (512 GB)

Can the Apple M3 Ultra (512 GB) run Jamba 1.5 Large?

75 pts

Yes, it runs well

Runs well. At Q5_K_M it needs about 315 GB of 384 GB usable, with an estimated speed of 3.8 tok/s.

Best quant: Q5_K_M
Generation speed: 3.8 tok/s
Prompt processing: 187 tok/s
First token (1K prompt): 5.5 s
Largest safe context: 256K

Download Jamba 1.5 Large

Original weights · Hugging Face

Full-precision files from AI21 Labs, for fine-tuning, vLLM, Transformers.

huggingface.co/ai21labs/AI21-Jamba-Large-1.5 (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

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

How the A 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.	30.6 / 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.	4.6 / 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
Total	75.2 / 100	75 ptsGreat (A) · 75 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 4.6/15, 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 Apple M3 Ultra (512 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	191 GB	384 GB	7.6 tok/s	Runs well	65 ptsGood (B) · 65 of 100 points: Model quality 22.1/45, Memory fit 25.0/25, Speed 6.5/15, Memory use 11.5/15	All files (opens in a new tab)
`Q3_K_M`	227 GB	384 GB	6.0 tok/s	Runs well	70 ptsGood (B) · 70 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 13.6/15	All files (opens in a new tab)
`Q4_K_M`	275 GB	384 GB	4.6 tok/s	Runs well	75 ptsGreat (A) · 75 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 5.1/15, Memory use 15.0/15	All files (opens in a new tab)
`Q5_K_M`	315 GB	384 GB	3.8 tok/s	Runs well	75 ptsGreat (A) · 75 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 4.6/15, Memory use 15.0/15	All files (opens in a new tab)
`Q6_K`	358 GB	384 GB	3.2 tok/s	Tight fit	74 ptsGreat (A) · 74 of 100 points: Model quality 31.2/45, Memory fit 24.0/25, Speed 4.2/15, Memory use 15.0/15	All files (opens in a new tab)
`Q8_0`	454 GB	384 GB	2.0 tok/s	Heavy offload	53 ptsUsable (C) · 53 of 100 points: Model quality 31.5/45, Memory fit 4.0/25, Speed 3.3/15, Memory use 15.0/15	All files (opens in a new tab)
`F16`	829 GB	384 GB	—	Won't run	9 ptsWon't run (F) · 9 of 100 points: Model quality 9.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	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

67 ptsGood (B) · 67 of 100 points: Model quality 22.1/45, Memory fit 24.0/25, Speed 6.5/15, Memory use 15.0/15 Apple M3 Ultra (256 GB) Q2_K · 7.6 tok/s
46 ptsUsable (C) · 46 of 100 points: Model quality 22.1/45, Memory fit 4.0/25, Speed 5.9/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q2_K · 6.3 tok/s

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.