Skip to content

DeepSeek V4 Flash on M5 Max 128 GB: VRAM, speed and fit

DeepSeek V4 Flash at FP4 + FP8 needs 156 GB; the M5 Max 128 GB can use 96.0 GB. The smallest machine we checked that runs it is the RTX PRO 6000 Blackwell.

Text generation · Chat · Ollama / LM Studio

Won’t fit · on M5 Max 128 GB · FP4 + FP8 · Ollama / LM Studio · Chat

GPU memory
188 GB
of 128 GB
Context
8K
auto
Speed
n/a
First reply
n/a

Where the memory goes

Model
155 GB
Context
54 MB
Overhead
637 MB
OS
32.0 GB
Over by
60.1 GB
Memory
188 GB of 128 GB
Context
8K tokens · auto
Speed
Doesn’t run here
Running cost
Doesn’t run here · $287/mo on a cloud 4× A40

Validation: Not validated

What DeepSeek V4 Flash on M5 Max 128 GB was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable156 GB neededFails
Headroom5% freenoneFails
Context for chat16K or more–Not run
Writing speed15 tok/s or more–Not run
First replyunder 3 s, 2K prompt–Not run

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
DeepSeek V4 Flash
Parameters
284B, 13B active
Precision
FP4 + FP8
Context
8K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Max 128 GB
GPU can use
96.0 GB of 128 GB

Worth trying

  • 2× RTX PRO 6000 Blackwell: Runs it with 1M context
  • M5 Ultra · 256 GB: Runs it with 1M context
  • DGX Station GB300: Runs it with 1M context

Running cost

At home
n/a
Doesn’t run on this machine.
Renting instead
$287/mo
4× A40 at $2.36/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 unsloth/DeepSeek-V4-Flash-0731-GGUF
vLLM
vllm serve deepseek-ai/DeepSeek-V4-Flash-0731
MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V4-Flash-0731-2.4bit-mixed

DeepSeek V4 Flash on similar machines

  • Mac mini M4 Pro 24 GBToo big
  • Mac mini M4 Pro 48 GBToo big
  • Mac mini M4 Pro 64 GBToo big
  • M4 Max 128 GBJust misses
  • M3 Ultra 96 GBToo big
  • M3 Ultra 256 GBRuns
  • M3 Ultra 512 GBRuns
  • M5 Ultra 512 GBRuns

All machines: DeepSeek V4 Flash VRAM requirements. Everything that runs here: what can the M5 Max 128 GB run?

Other models that run on M5 Max 128 GB

Questions

Can DeepSeek V4 Flash run on M5 Max 128 GB?

DeepSeek V4 Flash at FP4 + FP8 needs 156 GB; the M5 Max 128 GB can use 96.0 GB. The smallest machine we checked that runs it is the RTX PRO 6000 Blackwell.

Shown at the closest setup. Report VR-1UDOK49, calculated Nov 22, 2026 from published specs, not benchmarked.