Run DeepSeek V4 Flash on M5 Max

DeepSeek V4 Flash runs at 39 tok/s on a 128 GB M5 Max, a community run reported by modelfit.io (MLX, Q2_K). It needs about 120 GB of unified memory. It is DeepSeek's 284B mixture-of-experts model (13B active), released under the MIT licence.

Speed
community39
tok/s
First Token
community0.4
seconds
RAM Needed
120
GB minimum
Engine
MLX
of this figure
Want to run DeepSeek V4 Flash faster — or step up to bigger models? Find your Mac →

The figure

This is a community run: a real run, reported by its source and linked below. The index records it as given and never adjusts it.

MetricValue
Tokens per secondcommunity39 tok/s
Provenancecommunity run · modelfit.io
QuantizationQ2_K
EngineMLX
Time to first token0.4s
Figure dated2026-08
Minimum RAM120 GB
Parameters284B MoE (13B active)
Chip bandwidth614 GB/s

Every figure for DeepSeek V4 Flash on the M5 Max

Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (120 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.

SpeedQuantEngineMac RAMContextSourceNote
community39 tok/sQ2_KMLX128 GB—modelfit.io—
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Setup: run DeepSeek V4 Flash on a Mac

Ollama — the index has not verified an Ollama tag for DeepSeek V4 Flash, so it doesn’t print one (a guessed tag fails with “pull model manifest: file does not exist”). Search the Ollama library →

MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:

pip install -U mlx-lm
mlx_lm.generate --model <repo-id> --prompt "Hello"

Downloads: Search the Ollama library → · Hugging Face model card →

The 39 tok/s figure above came from MLX at Q2_K; other runtimes and quants run at different speeds.

Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.

DeepSeek V4 Flash on other Apple Silicon chips

ChipSpeedQuantEngineBandwidth
M5 Ultraestimated45 tok/sQ4_K_MMLX1228 GB/s
M3 Ultraestimated32 tok/sQ4_K_MMLX819 GB/s
M3 Maxcommunity27 tok/sQ2_KMLX400 GB/s

For the estimated figures here, the bandwidth formula’s typical error for large MoEs is ±34% (mostly below the measured figure), against 70 measured runs of 18 models (how it is computed).

About DeepSeek V4 Flash

DeepSeek's 284B MoE model, ~39 tok/s on M5 Max. MIT license, LLMCheck capability 47/50.

MIT licence · 284B MoE · 1000K context · LLMCheck capability 47/50 · see its leaderboard rank →

Memory by context length

Estimated, not measured: the index’s minimum for DeepSeek V4 Flash (120 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. DeepSeek V4 compressed attention (repo inference/model.py): 21 layers keep 1/4-compressed latents (+ indexer keys), 20 keep 1/128, every layer a 128-token raw window; one 512-d latent per position, K and V shared. A 16-bit KV cache is the default in llama.cpp, Ollama, LM Studio and mlx-lm; a q8 cache halves the KV part. Coding agents hold 64K tokens or more. Runtimes also add a buffer that grows with context, so leave a few GB spare. macOS lets the GPU use only part of a Mac’s memory by default (figures for an M5 Max Mac, which runs macOS 26 or later): “fits” means within the GPU memory a Mac of that tier can use with the limit raised, a tier tagged raise GPU limit fits only after sudo sysctl iogpu.wired_limit_mb raises it (the tooltip has the exact command), and the last column is the smallest Mac memory size whose default limit holds it (the GPU memory limit).

ContextKV cache (16-bit)RAM neededRAM, q8 KVSmallest tier that fitsWithin the default GPU limit
8K~0.1 GB~120.0 GB~120.0 GB192–256 GB Macsame
32K~0.2 GB~120.2 GB~120.1 GB192–256 GB Macsame
64K (coding-agent context)~0.5 GB~120.4 GB~120.2 GB192–256 GB Macsame
128K~0.9 GB~120.9 GB~120.4 GB192–256 GB Macsame

System requirements

Macs with the M5 Max

🛒 Get a Mac that runs DeepSeek V4 Flash

DeepSeek V4 Flash needs about 120 GB of unified memory. These Apple Silicon Macs have enough to run it. Apple builds the higher-memory configurations to order; Amazon does not stock them, so the used option links Amazon Renewed listings.

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.

Compare More Models

See how DeepSeek V4 Flash stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard