Can Ornith 1.0 35B A3B run on Mac mini M2 24GB?

YES — With Q2_K

A78Great

Estimated from fit model

Ornith 1.0 35B A3B needs ~17.5 GB VRAM. Mac mini M2 24GB has 17.3 GB. With Q2_K quantization, expect ~13 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: Very lowStack: StandardBottleneck: Memory bandwidth

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.

Ornith 1.0 35B A3B at Q4_K_M needs 25.2 GB — too much for Mac mini M2 24GB (17.3 GB). Runs at Q2_K (17.5 GB) with low quality.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 25.2 GB, exceeds 17.3 GB available

25.2 GB required17.3 GB available

146% VRAM needed

7.9 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

6.0 tok/s

TTFT

32533 ms

Safe context

Memory

25.2 GB / 17.3 GB

Offload

30%

Memory breakdown

Weights21.4 GB

KV Cache0.3 GB

Runtime0.9 GB

Headroom2.6 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsOrnith 1.0 35B A3B on Mac mini M2 24GB
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: 6.0 tok/s decode · 32.5s TTFT (warm) · 15 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

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

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	6.0 tok/s	17622 ms	4K
Coding	F	Too heavy	6.0 tok/s	32533 ms	4K
Agentic Coding	F	Too heavy	5.9 tok/s	47977 ms	4K
Reasoning	F	Too heavy	6.0 tok/s	38449 ms	4K
RAG	F	Too heavy	5.9 tok/s	59971 ms	4K

Inference speed

Ornith 1.0 35B A3B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Ornith 1.0 35B A3B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~139 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	139.1	Fits
RTX 4090 24GB	24 GB	Q4_K_M	77.7	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	76.8	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	65.5	Offloads
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	64.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	62.1	Offloads
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	60.7	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	47.4	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	47.4	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	36.4	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	33.4	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	31.9	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	28.3	Too big
RTX 4070 12GB	12 GB	Q4_K_M	9.9	Too big
RTX 3060 12GB	12 GB	Q4_K_M	5.8	Too big
RTX 4060 8GB	8 GB	Q4_K_M	4.4	Too big

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 Ornith 1.0 35B A3B (35.099998474121094B params) fits at each quantization level on Mac mini M2 24GB (17.3 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	F0
Q3_K_S	3	17.2 GB	Low	F0
NVFP4	4	19.7 GB	Medium	F0
Q4_K_M	4	21.4 GB	Medium	F0
Q5_K_M	5	25.3 GB	High	F0
Q6_K	6	28.8 GB	High	F0
Q8_0	8	37.6 GB	Very High	F0
F16	16	72.0 GB	Maximum	F0

Get started

Copy-paste commands to run Ornith 1.0 35B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "deepreinforce-ai/Ornith-1.0-35B" \
  --hf-file "Ornith-1.0-35B-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Opções de upgrade

Hardware que roda bem Ornith 1.0 35B A3B

MacBook Pro M4 32GBMelhor custo-benefício

32 GB Unified (+8)120 GB/s (+20)

Makes the model fit on the accelerator instead of staying completely out of reach.10.8 tok/s decodificação

Makes the model fit on the accelerator instead of staying completely out of reach.

Raises estimated decode speed by about 80%.

~$799 MSRP

Mac mini M4 64GBOpção econômica

64 GB Unified (+40)120 GB/s (+20)

Makes the model fit on the accelerator instead of staying completely out of reach.13.1 tok/s decodificação

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$1,099 MSRP

Mac mini M4 32GBUpgrade Apple

32 GB Unified (+8)120 GB/s (+20)

Makes the model fit on the accelerator instead of staying completely out of reach.10.8 tok/s decodificação

Makes the model fit on the accelerator instead of staying completely out of reach.

Raises estimated decode speed by about 80%.

~$1,099 MSRP

RTX 5090 32GBMaior salto

32 GB VRAM (+8)1792 GB/s (+1692)

Makes the model fit on the accelerator instead of staying completely out of reach.139.1 tok/s decodificação

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$1,999 MSRP

Frequently asked questions

Can Mac mini M2 24GB run Ornith 1.0 35B A3B?

Yes, Mac mini M2 24GB can run Ornith 1.0 35B A3B at Q2_K quantization (Runs with offload (needs ~0.2 GB host RAM)). The recommended Q4_K_M requires 25.2 GB which exceeds available memory, but at Q2_K it needs only 17.5 GB. Expected decode speed: 12.7 tok/s.

How much VRAM does Ornith 1.0 35B A3B need?

Ornith 1.0 35B A3B (35.099998474121094B parameters) requires approximately 25.2 GB at Q4_K_M quantization. On Mac mini M2 24GB, it fits at Q2_K using 17.5 GB.

What is the best quantization for Ornith 1.0 35B A3B?

The recommended quantization is Q4_K_M, but on Mac mini M2 24GB the best fitting quantization is Q2_K, which uses 17.5 GB.

What speed will Ornith 1.0 35B A3B run at on Mac mini M2 24GB?

On Mac mini M2 24GB, Ornith 1.0 35B A3B achieves approximately 12.7 tokens per second decode speed with a time-to-first-token of 15207ms using Q2_K quantization.

Can Mac mini M2 24GB run Ornith 1.0 35B A3B for coding?

For coding workloads, Ornith 1.0 35B A3B on Mac mini M2 24GB receives a F grade with 6.0 tok/s and 4K context.

What context window can Ornith 1.0 35B A3B use on Mac mini M2 24GB?

On Mac mini M2 24GB, Ornith 1.0 35B A3B can safely use up to 5K tokens of context at Q2_K quantization. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Ornith 1.0 35B A3B feels slow on Mac mini M2 24GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Is unified memory on Mac mini M2 24GB as fast as VRAM for Ornith 1.0 35B A3B?

Not always. Mac mini M2 24GB 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 mini M2 24GB See all hardware for Ornith 1.0 35B A3B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/ornith-1.0-35b-a3b-on-m2-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: