Can Hermes 4.3 36B run on Mac mini M4 64GB?

YES — Runs Great

C47Usable

▲Estimated — low-sample bucket· few comparable runs

Hermes 4.3 36B needs ~34.0 GB VRAM. Mac mini M4 64GB has 46.1 GB. With Q4_K_M quantization, expect ~4 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: 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) — 34.0 GB, 7.1 tok/s, Runs well

34.0 GB required46.1 GB available

74% VRAM used

Fit status

Runs well

Decode

7.1 tok/s

TTFT

27337 ms

Safe context

62K

Memory

34.0 GB / 46.1 GB

Memory breakdown

Weights22.0 GB

KV Cache4.2 GB

Runtime0.9 GB

Headroom6.9 GB

See how fast it feels

See how fast it feelsHermes 4.3 36B on Mac mini M4 64GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.

Given information:
 - Speed = 60 mph (miles per hour)
 - Time = 2.5 hours

Formula: Distance = Speed x Time

Calculation:
 Distance = 60 mph x 2.5 h
 = 150 miles

The train travels 150 miles.

Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.

Breakdown:
 - First half: 1.25 hours at 60 mph = 75 miles
 - Stop: 20 minutes (no distance)
 - Second half: 1.25 hours at 60 mph = 75 miles

Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph

The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 7.1 tok/s decode · 27.3s TTFT (warm) · 18 tok/s prefill

What limits this setup

The model fits in shared memory, but shared-memory bandwidth is now the real limiter.

Fit does not mean dedicated-VRAM speed

Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.

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

Prioritize bandwidth, not only capacity

If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	7.1 tok/s	14911 ms	62K
Coding	C	Runs well	3.9 tok/s	49207 ms	62K
Agentic Coding	C	Tight fit	7.1 tok/s	39763 ms	62K
Reasoning	C	Runs well	7.1 tok/s	32307 ms	62K
RAG	C	Tight fit	7.1 tok/s	49704 ms	62K