Can the Apple M3 (8 GB) run Yi Coder 9B Chat?

Yes, it runs well (over GPU memory limit)

Runs well (over GPU memory limit). At Q2_K it needs about 5.4 GB of 5.4 GB usable, with an estimated speed of 16.7 tok/s.

Best quant: Q2_K
Generation speed: 16.7 tok/s
Prompt processing: 288 tok/s
First token (1K prompt): 3.6 s
Largest safe context: 7K

Best app to run it on the Apple M3 (8 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open Yi Coder 9B Chat in LM Studio

Ollama Splits the model between GPU memory and system RAM, which this setup needs.
llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.

Want an agent? Yi Coder 9B Chat supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Yi Coder 9B Chat

Recommended for the Apple M3 (8 GB): Q2_K. 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.

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

ollama run yi-coder:9b-chat-q2_K

Quantized files · GGUF

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

Download the Q2_K file (opens in a new tab)

huggingface.co/bartowski/Yi-Coder-9B-Chat-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Yi-Coder-9B-Chat-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/01-ai/Yi-Coder-9B-Chat (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs wellover GPU memory limit: How well it runs on the Apple M3 (8 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	12.6 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	9.7 / 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
Match score	47.3 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Apple M3 (8 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	5.4 GB	5.4 GB	16.7 tok/s	Runs wellover GPU memory limit	28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	6.2 GB	5.4 GB	13.2 tok/s	Slowfar over GPU memory limit	33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	7.2 GB	5.4 GB	—	Won't run	38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	8.1 GB	5.4 GB	—	Won't run	38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	9.1 GB	5.4 GB	—	Won't run	39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	11.2 GB	5.4 GB	—	Won't run	40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	19.5 GB	5.4 GB	—	Won't run	40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	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

40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 47.6 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 52.1 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 63.4 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 67.9 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 F16 · 58.4 tok/s · Runs great
39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q6_K · 48.6 tok/s · Runs great

Quick answers

How much memory does Yi Coder 9B Chat need on the M3 8GB?

At Q2_K it needs about 5.4 GB. The M3 8GB has 5.4 GB usable.

How fast is Yi Coder 9B Chat on the M3 8GB?

About 16.7 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Yi Coder 9B Chat should I use on the M3 8GB?

Q2_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.