DeepSeek Coder 6.7B Instruct on ZhaoXin KX-U6580 NAS (64 GB)

Can the ZhaoXin KX-U6580 NAS (64 GB) run DeepSeek Coder 6.7B Instruct?

Yes, but slowly

Slow. At Q3_K_M it needs about 12.5 GB of 54.4 GB usable, with an estimated speed of 3.5 tok/s.

Best quant: Q3_K_M
Generation speed: 3.5 tok/s
Prompt processing: 3.7 tok/s
First token (1K prompt): 276.1 s
Largest safe context: 16K

Best app to run it on the ZhaoXin KX-U6580 NAS (64 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-coder:6.7b-instruct-q3_K_M

llama.cpp Usually the first to support new model architectures.
KoboldCpp

Want an agent? DeepSeek Coder 6.7B Instruct 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, 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 Coder 6.7B Instruct

Recommended for the ZhaoXin KX-U6580 NAS (64 GB): Q3_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-coder:6.7b-instruct-q3_K_M

Quantized files · GGUF

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

Download the Q3_K_M file (opens in a new tab)

huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF (opens in a new tab)

ollama run hf.co/TheBloke/deepseek-coder-6.7B-instruct-GGUF:Q3_K_M

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from DeepSeek. The weights themselves download from Hugging Face.

github.com/deepseek-ai/DeepSeek-Coder (opens in a new tab)

git clone https://github.com/deepseek-ai/DeepSeek-Coder

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

How it’s rated

Quality 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q3_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 Slow: How well it runs on the ZhaoXin KX-U6580 NAS (64 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.	12.9 / 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.	4.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	5.3 / 15
Match score	47.6 / 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 ZhaoXin KX-U6580 NAS (64 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	11.9 GB	54.4 GB	4.4 tok/s	Slow	23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	12.5 GB	54.4 GB	3.5 tok/s	Slow	28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	13.4 GB	54.4 GB	2.7 tok/s	Very slow	32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	14.0 GB	54.4 GB	2.2 tok/s	Very slow	32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	14.8 GB	54.4 GB	1.9 tok/s	Very slow	33Basic quality (D) · 33 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	16.4 GB	54.4 GB	1.4 tok/s	Very slow	34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	22.7 GB	54.4 GB	0.6 tok/s	Very slow	34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (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

34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 51.1 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 62.3 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 68.2 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 F16 · 43.1 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5060 Ti 16GB Q8_0 · 41.5 tok/s · Runs great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 83.1 tok/s · Runs great

Quick answers

How much memory does DeepSeek Coder 6.7B Instruct need on the ZhaoXin KX-U6580 NAS 64GB?

At Q3_K_M it needs about 12.5 GB. The ZhaoXin KX-U6580 NAS 64GB has 54.4 GB usable.

How fast is DeepSeek Coder 6.7B Instruct on the ZhaoXin KX-U6580 NAS 64GB?

About 3.5 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek Coder 6.7B Instruct should I use on the ZhaoXin KX-U6580 NAS 64GB?

Q3_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.