Can the Apple M2 Pro (32 GB) run Yi 34B Chat?

60 pts

Yes, with little memory to spare

Tight fit. At Q3_K_M it needs about 20.2 GB of 21.4 GB usable, with an estimated speed of 7.9 tok/s.

Best quant: Q3_K_M
Generation speed: 7.9 tok/s
Prompt processing: 123 tok/s
First token (1K prompt): 8.4 s
Largest safe context: 4K

Download Yi 34B Chat

Recommended for the Apple M2 Pro (32 GB): Q3_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run yi:34b-chat-q3_K_M

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

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

Download the Q3_K_M file (opens in a new tab)

huggingface.co/mradermacher/Yi-34B-Chat-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/Yi-34B-Chat-i1-GGUF:Q3_K_M

Original weights · Hugging Face

Full-precision files from 01.AI, for fine-tuning, vLLM, Transformers.

huggingface.co/01-ai/Yi-34B-Chat (opens in a new tab)

No sign-in needed.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How the B 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.	15.1 / 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.	6.7 / 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	60.8 / 100	60 ptsGood (B) · 60 of 100 points: Model quality 15.1/45, Memory fit 24.0/25, Speed 6.7/15, 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 M2 Pro (32 GB)

Quant	Memory needed	Available	Speed	Fit	Grade · points	Download
`Q2_K`	17.1 GB	21.4 GB	10.1 tok/s	Runs well	60 ptsGood (B) · 60 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 7.5/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q3_K_M`	20.2 GB	21.4 GB	7.9 tok/s	Tight fit	60 ptsGood (B) · 60 of 100 points: Model quality 15.1/45, Memory fit 24.0/25, Speed 6.7/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q4_K_M`	24.3 GB	21.4 GB	5.2 tok/s	Heavy offload	41 ptsPoor (D) · 41 of 100 points: Model quality 17.1/45, Memory fit 4.0/25, Speed 5.4/15, Memory use 15.0/15	GGUF (opens in a new tab)
`Q5_K_M`	27.7 GB	21.4 GB	—	Won't run	5 ptsWon't run (F) · 5 of 100 points: Model quality 5.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q6_K`	31.5 GB	21.4 GB	—	Won't run	5 ptsWon't run (F) · 5 of 100 points: Model quality 5.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	GGUF (opens in a new tab)
`Q8_0`	39.8 GB	21.4 GB	—	Won't run	5 ptsWon't run (F) · 5 of 100 points: Model quality 5.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15
`F16`	72.1 GB	21.4 GB	—	Won't run	5 ptsWon't run (F) · 5 of 100 points: Model quality 5.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15	Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

72 ptsGreat (A) · 72 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q4_K_M · 64.0 tok/s
70 ptsGood (B) · 70 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15 NVIDIA GeForce RTX 4090 Q4_K_M · 36.0 tok/s
70 ptsGood (B) · 70 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 3090 Q3_K_M · 43.2 tok/s
69 ptsGood (B) · 69 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 15.0/15 AMD Radeon RX 7900 XTX Q3_K_M · 38.1 tok/s
66 ptsGood (B) · 66 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.3/15 NVIDIA RTX PRO 6000 Blackwell Q6_K · 44.4 tok/s
64 ptsGood (B) · 64 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 9.7/15, Memory use 12.7/15 Apple M4 Max (64 GB) Q4_K_M · 16.8 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.