Skip to content

Saiga Llama3 8B on Mac mini M4 24 GB: VRAM, speed and fit

Saiga Llama3 8B at 8-bit runs on the M4 24 GB with 8K of context at about 12 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 24 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
17.6 GB
of 24.0 GB
Context
8K
auto
Speed
12 tok/s
Reading speed
First reply
9.9 s
2K prompt

Where the memory goes

Model
7.9 GB
Context
1.0 GB
Overhead
635 MB
OS
8.0 GB
Free
6.4 GB
Memory
17.6 GB of 24.0 GB
Context
8K tokens · auto
Speed
12 tok/s · reading speed
First reply
9.9 s for a 2K prompt
Running cost
$0.85/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Not validated

What Saiga Llama3 8B on Mac mini M4 24 GB was checked against
CheckTargetResultStatus
Fits in GPU memory16.0 GB usable9.6 GB neededPass
Headroom5% free6.4 GB free (40%)Pass
Context for chat8K or more8KPass
Writing speed15 tok/s or more12 tok/sCheck
First replyunder 3 s, 2K prompt9.9 sFails

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Saiga Llama3 8B
Parameters
8B
Precision
8-bit (Q8_0)
Context
8K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 24 GB
GPU can use
16.0 GB of 24.0 GB

Running cost

At home
$0.85/mo
39 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf mradermacher/saiga_llama3_8b-GGUF
vLLM
vllm serve IlyaGusev/saiga_llama3_8b

Saiga Llama3 8B on similar machines

All machines: Saiga Llama3 8B VRAM requirements. Everything that runs here: what can the Mac mini M4 24 GB run?

Other models that run on Mac mini M4 24 GB

Questions

Can Saiga Llama3 8B run on Mac mini M4 24 GB?

Saiga Llama3 8B at 8-bit runs on the M4 24 GB with 8K of context at about 12 tokens a second.

Report VR-166RSJ8, calculated Nov 22, 2026 from published specs, not benchmarked.