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.

HemmingwayAI logo

Can the Apple M4 Pro (48 GB) run Hemmingway-1.5?

Hemmingway-1.5·26.9B·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 Hemmingway-1.5 fully in unified memory at Q8_0 (about 31 GB of 36 GB), at roughly 5.3 tokens/s.

best quant
Q8_0
needs
31 GB
usable
36 GB
est. speed
~5.3 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Hemmingway-1.5 page →

Every quantisation of Hemmingway-1.5 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 loss20 GBfits~9.2 tok/s
Q5_K_M Near-lossless23 GBfits~7.8 tok/s
Q6_K Near-lossless26 GBfits~6.8 tok/s
Q8_0 pickLossless31 GBfits~5.3 tok/s
FP16 / BF16 Lossless56 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 Hemmingway-1.5 on the Apple M4 Pro (48 GB)

Using Q8_0, the best fit for Apple M4 Pro (48 GB).

MLX · Apple Silicon with mlx-lmdocs
pip install mlx-lm
mlx_lm.generate --model NeosQ/Hemmingway-1.5-MTPLX-Q4 --prompt "Hello"

Use `mlx_lm.chat` with the same --model for an interactive chat.

MLX · OpenAI-compatible serverdocs
mlx_lm.server --model NeosQ/Hemmingway-1.5-MTPLX-Q4 --port 8080

API on http://localhost:8080/v1.

Ollama · Q8_0 straight from Hugging Facedocs
ollama run hf.co/bartowski/HemmingwayAI_Hemmingway-1.5-GGUF:Q8_0
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf bartowski/HemmingwayAI_Hemmingway-1.5-GGUF:Q8_0

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

LM Studio · Download with the lms CLIdocs
lms get bartowski/HemmingwayAI_Hemmingway-1.5-GGUF@Q8_0

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

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="HemmingwayAI/Hemmingway-1.5", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])

Chat models that fit the Apple M4 Pro (48 GB) comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
20.9BA4.2BQ8_0≈13 GBFits in memory~34 tok/sCommercial OK
31.2BA4.6BQ6_K≈32 GBFits in memory~40 tok/sCommercial OK
32.8BQ6_K≈29 GBFits in memory~5.6 tok/sCommercial OK
36BA3BQ6_K≈31 GBFits in memory~61 tok/sCommercial OK
30.5BA3BQ8_0≈33 GBFits in memory~47 tok/sCommercial OK
24BA2BQ8_0≈26 GBFits in memory~71 tok/sConditions

Other GPUs that run Hemmingway-1.5

Frequently asked questions

Can the Apple M4 Pro (48 GB) run Hemmingway-1.5?
Yes. The Apple M4 Pro (48 GB) runs Hemmingway-1.5 fully in unified memory at Q8_0 (about 31 GB of 36 GB), at roughly 5.3 tokens/s.
How fast does Hemmingway-1.5 run on the Apple M4 Pro (48 GB)?
An estimate from memory bandwidth gives about 5.3 tokens/s at Q8_0.
Which quantisation of Hemmingway-1.5 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.