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.

FINAL-Bench logo

Can the Apple M4 Max 40-core (128 GB) run Darwin-180B-RSI-R3?

Darwin-180B-RSI-R3·180B (61.6B active)·Apple M4 Max 40-core (128 GB)·128 GB unified memory

Saved in this browser, used on every model page.
Just about

Just about. At Q3_K_M it needs about 95 GB of the 96 GB available, so keep the context short, at roughly 10 tokens/s.

best quant
Q3_K_M
needs
95 GB
usable
96 GB
est. speed
~10 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Darwin-180B-RSI-R3 page →

Every quantisation of Darwin-180B-RSI-R3 on the Apple M4 Max 40-core (128 GB)

QuantQualityMemoryFitSpeed
Q2_K Heavy loss81 GBfits~15 tok/s
Q3_K_M pickNoticeable loss95 GBtight~10 tok/s
Q4_K_M Small loss108 GBtoo big—
Q5_K_M Near-lossless126 GBtoo big—
Q6_K Near-lossless146 GBtoo big—
Q8_0 Lossless188 GBtoo big—
FP16 / BF16 Lossless353 GBtoo big—

Speed is a bandwidth-based estimate for generating text (546 GB/s); prompt processing and long contexts are slower.

Measured speed on the Apple M4 Max 40-core (128 GB)

No community reports for this pair yet.

Report your own speed →

Run Darwin-180B-RSI-R3 on the Apple M4 Max 40-core (128 GB)

Using Q3_K_M, the best fit for Apple M4 Max 40-core (128 GB).

Ollama · Q3_K_M straight from Hugging Facedocs
ollama run hf.co/mradermacher/Darwin-180B-RSI-R3-GGUF:Q3_K_M
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf mradermacher/Darwin-180B-RSI-R3-GGUF:Q3_K_M

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

LM Studio · Download with the lms CLIdocs
lms get mradermacher/Darwin-180B-RSI-R3-GGUF@Q3_K_M

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="FINAL-Bench/Darwin-180B-RSI-R3", 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 Max 40-core (128 GB) comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
125BA10BQ5_K_M≈91 GBFits in memory~42 tok/sCommercial OK
124BA12BQ5_K_M≈88 GBFits in memory~35 tok/sCommercial OK
109BA18BQ6_K≈88 GBFits in memory~20 tok/sConditions
zai-org logoGLM-4.6Vzai-org
108BA14.3BQ5_K_M≈81 GBFits in memory~30 tok/sCommercial OK
73.4BQ8_0≈79 GBFits in memory~3.9 tok/sConditions
36BA3BQ8_0≈38 GBFits in memory~94 tok/sCommercial OK

Other GPUs that run Darwin-180B-RSI-R3

Frequently asked questions

Can the Apple M4 Max 40-core (128 GB) run Darwin-180B-RSI-R3?
Just about. At Q3_K_M it needs about 95 GB of the 96 GB available, so keep the context short, at roughly 10 tokens/s.
How fast does Darwin-180B-RSI-R3 run on the Apple M4 Max 40-core (128 GB)?
An estimate from memory bandwidth gives about 10 tokens/s at Q3_K_M.
Which quantisation of Darwin-180B-RSI-R3 should I use on the Apple M4 Max 40-core (128 GB)?
Q3_K_M: the largest one that fits. Expected quality: noticeable loss 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.