Can Yi Coder 9B run on Mac Studio M3 Ultra 96GB?

YES — Runs Great

B60Good

Estimated from fit model

Yi Coder 9B needs ~18.2 GB VRAM. Mac Studio M3 Ultra 96GB has 69.1 GB. With Q4_K_M quantization, expect ~110 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 18.2 GB, 110.3 tok/s, Runs well

18.2 GB required69.1 GB available

26% VRAM used

Fit status

Runs well

Decode

110.3 tok/s

TTFT

1755 ms

Safe context

131K

Memory

18.2 GB / 69.1 GB

Memory breakdown

Weights5.5 GB

KV Cache1.5 GB

Runtime0.9 GB

Headroom10.4 GB

See how fast it feels

See how fast it feelsYi Coder 9B on Mac Studio M3 Ultra 96GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers))  # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
    """Sort a list using the quicksort algorithm.

    Args:
        arr: List of integers to sort.

    Returns:
        A new sorted list.
    """
    if len(arr) <= 1:
        return arr
    pivot = arr[len(arr) // 2]
    left   = [x for x in arr if x < pivot]
    middle = [x for x in arr if x == pivot]
    right  = [x for x in arr if x > pivot]
    return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 110.3 tok/s decode · 1.8s TTFT (warm) · 276 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	110.3 tok/s	957 ms	131K
Coding	B	Runs well	110.3 tok/s	1755 ms	131K
Agentic Coding	B	Runs well	110.3 tok/s	2553 ms	131K
Reasoning	B	Runs well	110.3 tok/s	2074 ms	131K
RAG	B	Runs well	110.3 tok/s	3191 ms	131K

Inference speed

Yi Coder 9B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Yi Coder 9B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~126 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	126.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	126.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	126.0	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	126.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	121.0	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	110.3	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	91.9	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	87.2	Fits
RTX 4070 12GB	12 GB	Q4_K_M	74.9	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	74.3	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	74.3	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	47.5	Fits
RTX 3060 12GB	12 GB	Q4_K_M	47.1	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	43.6	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	38.3	Fits
RTX 4060 8GB	8 GB	Q4_K_M	23.3	Heavy offload

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Yi Coder 9B (9B params) fits at each quantization level on Mac Studio M3 Ultra 96GB (69.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.5 GB	Low	C52
Q3_K_S	3	4.4 GB	Low	C52
NVFP4	4	5.0 GB	Medium	C52
Q4_K_M	4	5.5 GB	Medium	C52
Q5_K_M	5	6.5 GB	High	C53
Q6_K	6	7.4 GB	High	C53
Q8_0	8	9.6 GB	Very High	C53
F16Best for your GPU	16	18.5 GB	Maximum	C55

Get started

Copy-paste commands to run Yi Coder 9B on your machine.

Run

lms load Yi-Coder-9B-Chat && lms server start

Frequently asked questions

Can Mac Studio M3 Ultra 96GB run Yi Coder 9B?

Yes, Mac Studio M3 Ultra 96GB can run Yi Coder 9B with a B grade (Runs well). Expected decode speed: 110.3 tok/s.

How much VRAM does Yi Coder 9B need?

Yi Coder 9B (9B parameters) requires approximately 18.2 GB of memory with Q4_K_M quantization.

What is the best quantization for Yi Coder 9B?

The recommended quantization for Yi Coder 9B is Q4_K_M, which balances quality and memory efficiency.

What speed will Yi Coder 9B run at on Mac Studio M3 Ultra 96GB?

On Mac Studio M3 Ultra 96GB, Yi Coder 9B achieves approximately 110.3 tokens per second decode speed with a time-to-first-token of 1755ms using Q4_K_M quantization.

Can Mac Studio M3 Ultra 96GB run Yi Coder 9B for coding?

For coding workloads, Yi Coder 9B on Mac Studio M3 Ultra 96GB receives a B grade with 110.3 tok/s and 131K context.

What context window can Yi Coder 9B use on Mac Studio M3 Ultra 96GB?

On Mac Studio M3 Ultra 96GB, Yi Coder 9B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M3 Ultra 96GB as fast as VRAM for Yi Coder 9B?

Not always. Mac Studio M3 Ultra 96GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.

See all results for Mac Studio M3 Ultra 96GB See all hardware for Yi Coder 9B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/yi-coder-9b-on-m3-ultra-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: