Can the Apple M4 (16 GB) run LFM3-VL-2B?
LFM3-VL-2B·1.9B·Apple M4 (16 GB)·16 GB unified memory
Yes. The Apple M4 (16 GB) runs LFM3-VL-2B fully in unified memory at FP16 / BF16 (about 4.3 GB of 11 GB), at roughly 17 tokens/s.
- best quant
- FP16 / BF16
- needs
- 4.3 GB
- usable
- 11 GB
- est. speed
- ~17 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the LFM3-VL-2B page →
Every quantisation of LFM3-VL-2B on the Apple M4 (16 GB)
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 1.6 GB | fits | ~105 tok/s |
| Q3_K_M | 1.7 GB | fits | ~70 tok/s |
| Q4_K_M | 1.9 GB | fits | ~57 tok/s |
| Q5_K_M | 2.1 GB | fits | ~48 tok/s |
| Q6_K | 2.3 GB | fits | ~42 tok/s |
| Q8_0 | 2.7 GB | fits | ~32 tok/s |
| FP16 / BF16 pick | 4.3 GB | fits | ~17 tok/s |
Speed is a bandwidth-based estimate for generating text (120 GB/s); prompt processing and long contexts are slower.
Measured speed on the Apple M4 (16 GB)
No community reports for this pair yet.
Report your own speed →Run LFM3-VL-2B on the Apple M4 (16 GB)
Using FP16 / BF16, the best fit for Apple M4 (16 GB).
ollama run lfm3-vl:2bThe library build picks its own default quantisation.
ollama run hf.co/LiquidAI/LFM3-VL-2B-GGUF:F16 llama-server -hf LiquidAI/LFM3-VL-2B-GGUF:F16brew install llama.cpp ships with Metal. Downloads the GGUF on first run.
lms get LiquidAI/LFM3-VL-2B-GGUF@F16Then load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="LiquidAI/LFM3-VL-2B", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Vision models that fit the Apple M4 (16 GB) comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 1.9B | Q8_0 | ≈2.7 GBFits in memory | ~32 tok/s | |
| 2.3B | Q8_0 | ≈2.8 GBFits in memory | ~27 tok/s | |
| 2.1B | Q8_0 | ≈3.2 GBFits in memory | ~29 tok/s | |
| 1.6B | Q8_0 | ≈1.9 GBFits in memory | ~40 tok/s | |
| 1.3B | Q8_0 | ≈1.7 GBFits in memory | ~48 tok/s | |
| 2.2B | Q8_0 | ≈2.6 GBFits in memory | ~28 tok/s |
Other GPUs that run LFM3-VL-2B
Frequently asked questions
- Can the Apple M4 (16 GB) run LFM3-VL-2B?
- Yes. The Apple M4 (16 GB) runs LFM3-VL-2B fully in unified memory at FP16 / BF16 (about 4.3 GB of 11 GB), at roughly 17 tokens/s.
- How fast does LFM3-VL-2B run on the Apple M4 (16 GB)?
- An estimate from memory bandwidth gives about 17 tokens/s at FP16 / BF16.
- Which quantisation of LFM3-VL-2B should I use on the Apple M4 (16 GB)?
- FP16 / BF16: the largest one that fits. Expected quality: lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.