Can LFM2.5 350M run on MacBook Pro M3 Max 128GB?

YES — Runs Great

C48Usable

Estimated from fit model

LFM2.5 350M needs ~15.1 GB VRAM. MacBook Pro M3 Max 128GB has 92.2 GB. With Q4_K_M quantization, expect ~5 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: 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) — 15.1 GB, 4.9 tok/s, Runs well

15.1 GB required92.2 GB available

16% VRAM used

Fit status

Runs well

Decode

4.9 tok/s

TTFT

39510 ms

Safe context

128K

Memory

15.1 GB / 92.2 GB

Memory breakdown

Weights0.2 GB

KV Cache0.2 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsLFM2.5 350M on MacBook Pro M3 Max 128GB
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: 4.9 tok/s decode · 39.5s TTFT (warm) · 12 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	4.9 tok/s	21551 ms	128K
Coding	C	Runs well	4.9 tok/s	39510 ms	128K
Agentic Coding	C	Runs well	4.9 tok/s	57469 ms	128K
Reasoning	C	Runs well	4.9 tok/s	46694 ms	128K
RAG	C	Runs well	4.9 tok/s	71837 ms	128K

Inference speed

LFM2.5 350M inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for LFM2.5 350M at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~7 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	6.6	Fits
RTX 4090 24GB	24 GB	Q4_K_M	5.6	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	5.6	Fits
RTX 4070 12GB	12 GB	Q4_K_M	5.6	Fits
RTX 4060 8GB	8 GB	Q4_K_M	5.6	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	4.9	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	4.9	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	4.9	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	4.9	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	4.9	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	4.9	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	4.9	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	4.9	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	4.9	Fits
RTX 3090 24GB	24 GB	Q4_K_M	4.2	Fits
RTX 3060 12GB	12 GB	Q4_K_M	4.2	Fits

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 LFM2.5 350M (0.3499999940395355B params) fits at each quantization level on MacBook Pro M3 Max 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	0.1 GB	Low	C51
Q3_K_S	3	0.2 GB	Low	C51
NVFP4	4	0.2 GB	Medium	C51
Q4_K_M	4	0.2 GB	Medium	C51
Q5_K_M	5	0.3 GB	High	C51
Q6_K	6	0.3 GB	High	C51
Q8_0	8	0.4 GB	Very High	C51
F16Best for your GPU	16	0.7 GB	Maximum	C51

Get started

Copy-paste commands to run LFM2.5 350M on your machine.

Run

lms load LFM2.5-350M && lms server start

Frequently asked questions

Can MacBook Pro M3 Max 128GB run LFM2.5 350M?

Yes, MacBook Pro M3 Max 128GB can run LFM2.5 350M with a C grade (Runs well). Expected decode speed: 4.9 tok/s.

How much VRAM does LFM2.5 350M need?

LFM2.5 350M (0.3499999940395355B parameters) requires approximately 15.1 GB of memory with Q4_K_M quantization.

What is the best quantization for LFM2.5 350M?

The recommended quantization for LFM2.5 350M is Q4_K_M, which balances quality and memory efficiency.

What speed will LFM2.5 350M run at on MacBook Pro M3 Max 128GB?

On MacBook Pro M3 Max 128GB, LFM2.5 350M achieves approximately 4.9 tokens per second decode speed with a time-to-first-token of 39510ms using Q4_K_M quantization.

Can MacBook Pro M3 Max 128GB run LFM2.5 350M for coding?

For coding workloads, LFM2.5 350M on MacBook Pro M3 Max 128GB receives a C grade with 4.9 tok/s and 128K context.

What context window can LFM2.5 350M use on MacBook Pro M3 Max 128GB?

On MacBook Pro M3 Max 128GB, LFM2.5 350M can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

What should I upgrade first if LFM2.5 350M feels slow on MacBook Pro M3 Max 128GB?

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.

Is unified memory on MacBook Pro M3 Max 128GB as fast as VRAM for LFM2.5 350M?

Not always. MacBook Pro M3 Max 128GB 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 Max 128GB See all hardware for LFM2.5 350M

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/lfm2.5-350m-on-m3-max-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: