selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

FreedomIntelligence logo

Can the Apple M4 Pro (48 GB) run HuatuoGPT-3-27B?

HuatuoGPT-3-27B·27B·Apple M4 Pro (48 GB)·48 GB unified memory

Saved in this browser, used on every model page.
Yes

Yes. The Apple M4 Pro (48 GB) runs HuatuoGPT-3-27B fully in unified memory at Q8_0 (about 31 GB of 36 GB), at roughly 5.2 tokens/s.

best quant
Q8_0
needs
31 GB
usable
36 GB
est. speed
~5.2 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the HuatuoGPT-3-27B page →

Every quantisation of HuatuoGPT-3-27B on the Apple M4 Pro (48 GB)

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~17 tok/s
Q3_K_M Noticeable loss16 GBfits~11 tok/s
Q4_K_M Small loss19 GBfits~9.2 tok/s
Q5_K_M Near-lossless21 GBfits~7.8 tok/s
Q6_K Near-lossless24 GBfits~6.8 tok/s
Q8_0 pickLossless31 GBfits~5.2 tok/s
FP16 / BF16 Lossless55 GBtoo big—

Speed is a bandwidth-based estimate for generating text (273 GB/s); prompt processing and long contexts are slower.

Measured speed on the Apple M4 Pro (48 GB)

No community reports for this pair yet.

Report your own speed →

Run HuatuoGPT-3-27B on the Apple M4 Pro (48 GB)

Using Q6_K, the best fit for Apple M4 Pro (48 GB).

Ollama · Q6_K straight from Hugging Facedocs
ollama run hf.co/mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q6_K
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf mradermacher/HuatuoGPT-3-27B-i1-GGUF:Q6_K

brew install llama.cpp ships with Metal. Downloads the GGUF on first run.

LM Studio · Download with the lms CLIdocs
lms get mradermacher/HuatuoGPT-3-27B-i1-GGUF@Q6_K

Then load it from the LM Studio app or with `lms load`.

Transformers · Ask about an imagedocs
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="FreedomIntelligence/HuatuoGPT-3-27B", 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 Pro (48 GB) comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
27.8BQ8_0≈31 GBFits in memory~5.1 tok/sCommercial OK
25.8BA4BQ8_0≈29 GBFits in memory~35 tok/sCommercial OK
27.8BQ8_0≈30 GBFits in memory~5.1 tok/sCommercial OK
31.3BQ6_K≈33 GBFits in memory~5.8 tok/sCommercial OK
27.4BQ8_0≈32 GBFits in memory~5.2 tok/sConditions
27.8BQ8_0≈30 GBFits in memory~5.1 tok/sCommercial OK

Other GPUs that run HuatuoGPT-3-27B

Frequently asked questions

Can the Apple M4 Pro (48 GB) run HuatuoGPT-3-27B?
Yes. The Apple M4 Pro (48 GB) runs HuatuoGPT-3-27B fully in unified memory at Q8_0 (about 31 GB of 36 GB), at roughly 5.2 tokens/s.
How fast does HuatuoGPT-3-27B run on the Apple M4 Pro (48 GB)?
An estimate from memory bandwidth gives about 5.2 tokens/s at Q8_0.
Which quantisation of HuatuoGPT-3-27B should I use on the Apple M4 Pro (48 GB)?
Q8_0: 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.