TinyLlama 1.1B Chat on Apple M2 Pro (32 GB)

Can the Apple M2 Pro (32 GB) run TinyLlama 1.1B Chat?

47 pts

Yes, it runs well

Runs well. At F16 it needs about 4.6 GB of 21.4 GB usable, with an estimated speed of 45.1 tok/s.

Best quant: F16
Generation speed: 45.1 tok/s
Prompt processing: 3,833 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 2K

Download TinyLlama 1.1B Chat

Recommended for the Apple M2 Pro (32 GB): F16. 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 tinyllama:1.1b-chat-v1-fp16

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.

huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF (opens in a new tab)

ollama run hf.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF

Original weights · Hugging Face

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

huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from TinyLlama. The weights themselves download from Hugging Face.

github.com/jzhang38/TinyLlama (opens in a new tab)

git clone https://github.com/jzhang38/TinyLlama

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

How the C 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.	2.7 / 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.	4.9 / 15
Total	47.6 / 100	47 ptsUsable (C) · 47 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15

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`	2.8 GB	21.4 GB	316 tok/s	Runs well	44 ptsUsable (C) · 44 of 100 points: Model quality 1.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15	GGUF (opens in a new tab)
`Q3_K_M`	2.9 GB	21.4 GB	248 tok/s	Runs well	45 ptsUsable (C) · 45 of 100 points: Model quality 2.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15	GGUF (opens in a new tab)
`Q4_K_M`	3.0 GB	21.4 GB	192 tok/s	Runs well	45 ptsUsable (C) · 45 of 100 points: Model quality 2.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15	GGUF (opens in a new tab)
`Q5_K_M`	3.1 GB	21.4 GB	159 tok/s	Runs well	46 ptsUsable (C) · 46 of 100 points: Model quality 2.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15	GGUF (opens in a new tab)
`Q6_K`	3.3 GB	21.4 GB	133 tok/s	Runs well	46 ptsUsable (C) · 46 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15	GGUF (opens in a new tab)
`Q8_0`	3.5 GB	21.4 GB	97.8 tok/s	Runs well	46 ptsUsable (C) · 46 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15	GGUF (opens in a new tab)
`F16`	4.6 GB	21.4 GB	45.1 tok/s	Runs well	47 ptsUsable (C) · 47 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15	Original weights (opens in a new tab)

Memory figures assume 2K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

52 ptsUsable (C) · 52 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.4/15 NVIDIA GeForce RTX 4060 F16 · 71.2 tok/s
49 ptsUsable (C) · 49 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 Intel Arc B580 F16 · 91.2 tok/s
49 ptsUsable (C) · 49 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 NVIDIA GeForce RTX 3060 12GB F16 · 94.3 tok/s
49 ptsUsable (C) · 49 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15 NVIDIA GeForce RTX 4070 SUPER F16 · 132 tok/s
48 ptsUsable (C) · 48 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 Apple M4 Pro (24 GB) F16 · 61.5 tok/s
48 ptsUsable (C) · 48 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15 Apple M4 (16 GB) Q8_0 · 58.7 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.