DeepSeek V2.5 on Apple M3 Ultra (256 GB)

Can the Apple M3 Ultra (256 GB) run DeepSeek V2.5?

Yes, it runs great

Runs great. At Q4_K_M it needs about 160 GB of 192 GB usable, with an estimated speed of 36.2 tok/s.

Best quant: Q4_K_M
Generation speed: 36.2 tok/s
Prompt processing: 838 tok/s
First token (1K prompt): 1.2 s
Largest safe context: 160K

Best app to run it on the Apple M3 Ultra (256 GB)

On macOS

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run deepseek-v2.5:236b

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

Want an agent? DeepSeek V2.5 supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download DeepSeek V2.5

Recommended for the Apple M3 Ultra (256 GB): Q4_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run deepseek-v2.5:236b

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M files (opens in a new tab)

huggingface.co/bartowski/DeepSeek-V2.5-GGUF (opens in a new tab)

ollama run hf.co/bartowski/DeepSeek-V2.5-GGUF

Original weights · Hugging Face

Full-precision files from DeepSeek, for fine-tuning, vLLM, Transformers.

huggingface.co/deepseek-ai/DeepSeek-V2.5 (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the Apple M3 Ultra (256 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	29.9 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	14.3 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	84.2 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the Apple M3 Ultra (256 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	111 GB	192 GB	55.9 tok/s	Runs great	49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q3_K_M`	132 GB	192 GB	45.4 tok/s	Runs great	58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (Q3_K_L) · folder (opens in a new tab)
`Q4_K_M`	160 GB	192 GB	36.2 tok/s	Runs great	66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	184 GB	192 GB	30.4 tok/s	Runs welltight fit	67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	210 GB	192 GB	22.0 tok/s	Runs wellover GPU memory limit	69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	266 GB	192 GB	—	Won't run	70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	488 GB	192 GB	—	Won't run	70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q3_K_M · 44.5 tok/s · Runs well (tight fit)
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 36.2 tok/s · Runs great
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) Q2_K · 24.2 tok/s · Runs well (tight fit)
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q2_K · 63.5 tok/s · Runs well (offloads to RAM)
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (128 GB) Q2_K · 33.6 tok/s · Runs well (over GPU memory limit)
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) Q2_K · 22.5 tok/s · Runs well (over GPU memory limit)

Quick answers

How much memory does DeepSeek V2.5 need on the M3 Ultra 256GB?

At Q4_K_M it needs about 160 GB. The M3 Ultra 256GB has 192 GB usable.

How fast is DeepSeek V2.5 on the M3 Ultra 256GB?

About 36.2 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek V2.5 should I use on the M3 Ultra 256GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.