Can Ornith 1.0 35B A3B run on MacBook Pro M3 Pro 36GB?

YES — With Offload

A79Great

Estimated from fit model

Ornith 1.0 35B A3B needs ~26.5 GB VRAM. MacBook Pro M3 Pro 36GB has 25.9 GB. With Q4_K_M quantization, expect ~16 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 26.5 GB, 15.8 tok/s, Runs with offload (needs ~0.5 GB host RAM)

26.5 GB required25.9 GB available

102% VRAM needed

0.6 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~0.5 GB host RAM)

Decode

15.8 tok/s

TTFT

12236 ms

Safe context

Memory

26.5 GB / 25.9 GB

Memory breakdown

Weights21.4 GB

KV Cache0.3 GB

Runtime0.9 GB

Headroom3.9 GB

See how fast it feels

See how fast it feelsOrnith 1.0 35B A3B on MacBook Pro M3 Pro 36GB
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: 15.8 tok/s decode · 12.2s TTFT (warm) · 40 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	A	Runs with offload (needs ~0.4 GB host RAM)	16.0 tok/s	6605 ms	4K
Coding	A	Runs with offload (needs ~0.5 GB host RAM)	15.8 tok/s	12236 ms	4K
Agentic Coding	A	Runs with offload (needs ~0.7 GB host RAM)	15.5 tok/s	18146 ms	4K
Reasoning	A	Runs with offload (needs ~0.5 GB host RAM)	15.8 tok/s	14460 ms	4K
RAG	A	Runs with offload (needs ~0.7 GB host RAM)	15.5 tok/s	22682 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 MacBook Pro M3 Pro 36GB (25.9 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	A80
Q3_K_S	3	17.2 GB	Low	A80
NVFP4Best for your GPU	4	19.7 GB	Medium	A80
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

Frequently asked questions

Can MacBook Pro M3 Pro 36GB run Ornith 1.0 35B A3B?

Yes, MacBook Pro M3 Pro 36GB can run Ornith 1.0 35B A3B with a A grade (Runs with offload (needs ~0.5 GB host RAM)). Expected decode speed: 15.8 tok/s.

How much VRAM does Ornith 1.0 35B A3B need?

Ornith 1.0 35B A3B (35.099998474121094B parameters) requires approximately 26.5 GB of memory with Q4_K_M quantization.

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

The recommended quantization for Ornith 1.0 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Ornith 1.0 35B A3B run at on MacBook Pro M3 Pro 36GB?

On MacBook Pro M3 Pro 36GB, Ornith 1.0 35B A3B achieves approximately 15.8 tokens per second decode speed with a time-to-first-token of 12236ms using Q4_K_M quantization.

Can MacBook Pro M3 Pro 36GB run Ornith 1.0 35B A3B for coding?

For coding workloads, Ornith 1.0 35B A3B on MacBook Pro M3 Pro 36GB receives a A grade with 15.8 tok/s and 4K context.

What context window can Ornith 1.0 35B A3B use on MacBook Pro M3 Pro 36GB?

On MacBook Pro M3 Pro 36GB, Ornith 1.0 35B A3B can safely use up to 4K tokens of context. 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 MacBook Pro M3 Pro 36GB?

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 MacBook Pro M3 Pro 36GB as fast as VRAM for Ornith 1.0 35B A3B?

Not always. MacBook Pro M3 Pro 36GB 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 MacBook Pro M3 Pro 36GB 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-m3-pro-36gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: