Skip to content

OTel 2.0 LLM 31B IT on Mac mini M4 32 GB: VRAM, speed and fit

OTel 2.0 LLM 31B IT at 4-bit runs on the M4 32 GB with 20K of context at about 5.1 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 32 GB · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat

GPU memory
30.8 GB
of 32.0 GB
Context
20K
auto
Speed
5.1 tok/s
Slow
First reply
42 s
2K prompt

Where the memory goes

Model
17.7 GB
Context
1.6 GB
Overhead
936 MB
OS
10.7 GB
Free
1.2 GB
Memory
30.8 GB of 32.0 GB
Context
20K tokens · auto
Speed
5.1 tok/s · slow
First reply
42 s for a 2K prompt
Running cost
$0.85/mo at home · $33/mo on a cloud RTX A5000

Validation: Not validated

What OTel 2.0 LLM 31B IT on Mac mini M4 32 GB was checked against
CheckTargetResultStatus
Fits in GPU memory21.3 GB usable20.1 GB neededPass
Headroom5% free1.2 GB free (6%)Pass
Context for chat16K or more20KPass
Writing speed15 tok/s or more5.1 tok/sFails
First replyunder 3 s, 2K prompt42 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
OTel 2.0 LLM 31B IT
Parameters
31.3B
Precision
4-bit (Q4_K_M)
Context
20K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 32 GB
GPU can use
21.3 GB of 32.0 GB

Worth trying

  • 8-bit cache: Room for 60K context

Running cost

At home
$0.85/mo
39 W at the wall
Renting instead
$33/mo
RTX A5000 at $0.27/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 wfakhri/OTel-2.0-LLM-31B-IT-GGUF
vLLM
vllm serve farbodtavakkoli/OTel-2.0-LLM-31B-IT

OTel 2.0 LLM 31B IT on similar machines

All machines: OTel 2.0 LLM 31B IT VRAM requirements. Everything that runs here: what can the Mac mini M4 32 GB run?

Other models that run on Mac mini M4 32 GB

Questions

Can OTel 2.0 LLM 31B IT run on Mac mini M4 32 GB?

OTel 2.0 LLM 31B IT at 4-bit runs on the M4 32 GB with 20K of context at about 5.1 tokens a second.

Report VR-1QHH8UW, calculated Nov 22, 2026 from published specs, not benchmarked.