MacBook Pro M4 32GBコスパ重視
32 GB Unified (+16)
C
Adds memory headroom for longer context windows and future model growth.4.9 tok/sデコード
Adds memory headroom for longer context windows and future model growth.
〜$799 MSRP
Can LFM2.5 350M run on RTX 4080 Super 16GB?
YES — Runs Great
C49Usable
Estimated from fit model
LFM2.5 350M needs ~2.9 GB VRAM. RTX 4080 Super 16GB has 16.0 GB. With Q4_K_M quantization, expect ~6 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: 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.
Select quantization to explore
Q4_K_M (Medium quality) — 2.9 GB, 5.6 tok/s, Runs well
2.9 GB required16.0 GB available
18% VRAM used
Fit status
Runs well
Decode
5.6 tok/s
TTFT
34571 ms
Safe context
128K
Memory
2.9 GB / 16.0 GB
Memory breakdown
Weights0.2 GB
KV Cache0.2 GB
Runtime0.9 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsLFM2.5 350M on RTX 4080 Super 16GB
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: 5.6 tok/s decode · 34.6s TTFT (warm) · 14 tok/s prefill
What limits this setup
This model fits, but memory bandwidth is the part holding decode speed back.
Throughput will feel slow
Estimated decode speed is only 5.6 tok/s, so this is more of a technical fit than a comfortable daily-driver setup.
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 | 5.6 tok/s | 18857 ms | 128K |
| Coding | C | Runs well | 5.6 tok/s | 34571 ms | 128K |
| Agentic Coding | C | Runs well | 5.6 tok/s | 50286 ms | 128K |
| Reasoning | C | Runs well | 5.6 tok/s | 40857 ms | 128K |
| RAG | C | Runs well | 5.6 tok/s | 62857 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 RTX 4080 Super 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.1 GB | Low | B57 |
Q3_K_S | 3 | 0.2 GB | Low | B57 |
NVFP4 | 4 | 0.2 GB | Medium | B57 |
Q4_K_M | 4 | 0.2 GB | Medium | B57 |
Q5_K_M | 5 | 0.3 GB | High | B57 |
Q6_K | 6 | 0.3 GB | High | B57 |
Q8_0 | 8 | 0.4 GB | Very High | B57 |
F16Best for your GPU | 16 | 0.7 GB | Maximum | B57 |
Get started
Copy-paste commands to run LFM2.5 350M on your machine.
Run
lms load LFM2.5-350M && lms server startアップグレードオプション
LFM2.5 350Mを快適に動かすハードウェア
Frequently asked questions
Can RTX 4080 Super 16GB run LFM2.5 350M?
Yes, RTX 4080 Super 16GB can run LFM2.5 350M with a C grade (Runs well). Expected decode speed: 5.6 tok/s.
How much VRAM does LFM2.5 350M need?
LFM2.5 350M (0.3499999940395355B parameters) requires approximately 2.9 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 RTX 4080 Super 16GB?
On RTX 4080 Super 16GB, LFM2.5 350M achieves approximately 5.6 tokens per second decode speed with a time-to-first-token of 34571ms using Q4_K_M quantization.
Can RTX 4080 Super 16GB run LFM2.5 350M for coding?
For coding workloads, LFM2.5 350M on RTX 4080 Super 16GB receives a C grade with 5.6 tok/s and 128K context.
What context window can LFM2.5 350M use on RTX 4080 Super 16GB?
On RTX 4080 Super 16GB, 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 RTX 4080 Super 16GB?
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.
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-rtx-4080-super-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: