on

Can the Intel Core Ultra 5 125H NAS (96 GB) run DeepSeek LLM 67B Chat?

39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.

Barely: it runs very slowly

Very slow. At Q6_K it needs about 64.1 GB of 83.5 GB usable, with an estimated speed of 0.8 tok/s.

Best quant
Q6_K
Generation speed
0.8 tok/s
Prompt processing
5.3 tok/s
First token (1K prompt)
193.3 s
Largest safe context
4K

Best app to run it on the Intel Core Ultra 5 125H NAS (96 GB)

On Linux

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-llm:67b

How we choose: the files published for this model, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download DeepSeek LLM 67B Chat

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-llm:67b

Quantized files · GGUF

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

huggingface.co/mradermacher/deepseek-llm-67b-chat-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/deepseek-llm-67b-chat-i1-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/deepseek-llm-67b-chat (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 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at Q6_K, 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 Very slow
How well it runs on the Intel Core Ultra 5 125H NAS (96 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.17.8 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); 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.2.1 / 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 score59.9 / 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 Intel Core Ultra 5 125H NAS (96 GB)

Quant Memory needed Available Speed Runs Quality Download
Q2_K 35.8 GB 83.5 GB 1.9 tok/s Very slow 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 41.9 GB 83.5 GB 1.5 tok/s Very slow 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 50.0 GB 83.5 GB 1.2 tok/s Very slow 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 56.7 GB 83.5 GB 1.0 tok/s Very slow 38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 64.1 GB 83.5 GB 0.8 tok/s Very slow 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q8_0 80.3 GB 83.5 GB 0.6 tok/s Very slowtight fit 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
F16 144 GB 83.5 GB — Won't run 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does DeepSeek LLM 67B Chat need on the Intel Core Ultra 5 125H NAS 96GB?

At Q6_K it needs about 64.1 GB. The Intel Core Ultra 5 125H NAS 96GB has 83.5 GB usable.

How fast is DeepSeek LLM 67B Chat on the Intel Core Ultra 5 125H NAS 96GB?

About 0.8 tok/s at Q6_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek LLM 67B Chat should I use on the Intel Core Ultra 5 125H NAS 96GB?

Q6_K. 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.

Was this page helpful?