VOOZH about

URL: https://willitrunai.com/can-run/dolphin-2.9-8b-on-m4-max-36gb

⇱ Dolphin 2.9 8B on MacBook Pro M4 Max 36GB? YES

Can Dolphin 2.9 8B run on MacBook Pro M4 Max 36GB?

YES — Runs Great

C51Usable
○Estimated from fit model

Dolphin 2.9 8B needs ~11.6 GB VRAM. MacBook Pro M4 Max 36GB has 25.9 GB. With Q4_K_M quantization, expect ~62 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: Balanced
Share:

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) — 11.6 GB, 62.0 tok/s, Runs well
11.6 GB required25.9 GB available
45% VRAM used

Fit status

Runs well

Decode

62.0 tok/s

TTFT

3122 ms

Safe context

33K

Memory

11.6 GB / 25.9 GB

Memory breakdown

Weights4.9 GB
KV Cache2.0 GB
Runtime0.9 GB
Headroom3.9 GB

See how fast it feels

See how fast it feelsDolphin 2.9 8B on MacBook Pro M4 Max 36GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API. When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed. Key benefits of running locally: - Full privacy: your prompts never leave your machine - No per-token cost or rate limits - Works offline once the model is downloaded - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb: Model size Q4 (4-bit) Q8 (8-bit) FP16 7B params ~4.3 GB ~7.5 GB ~14 GB 13B params ~7.9 GB ~13.9 GB ~26 GB 70B params ~42.7 GB ~74.9 GB ~140 GB Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 62.0 tok/s decode · 3.1s TTFT (warm) · 155 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

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well62.0 tok/s1703 ms33K
CodingCRuns well62.0 tok/s3122 ms33K
Agentic CodingCRuns well62.0 tok/s4540 ms33K
ReasoningCRuns well62.0 tok/s3689 ms33K
RAGCRuns well62.0 tok/s5675 ms33K

Quantization options

How Dolphin 2.9 8B (8B params) fits at each quantization level on MacBook Pro M4 Max 36GB (25.9 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
3.1 GB
LowC45
Q3_K_S
3
3.9 GB
LowC45
NVFP4
4
4.5 GB
MediumC45
Q4_K_M
4
4.9 GB
MediumC46
Q5_K_M
5
5.8 GB
HighC46
Q6_K
6
6.6 GB
HighC46
Q8_0
8
8.6 GB
Very HighC48
F16Best for your GPU
16
16.4 GB
MaximumC50

Get started

Copy-paste commands to run Dolphin 2.9 8B on your machine.

Run

ollama run dolphin-llama3

Frequently asked questions

See all results for MacBook Pro M4 Max 36GBSee all hardware for Dolphin 2.9 8B