DeepSeek MoE 16B Chat on Intel Core Ultra 200V (Arc 140V) (16 GB)

Can the Intel Core Ultra 200V (Arc 140V) (16 GB) run DeepSeek MoE 16B Chat?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q2_K it needs about 8.8 GB of 9.1 GB usable, with an estimated speed of 60.8 tok/s.

Best quant: Q2_K
Generation speed: 60.8 tok/s
Prompt processing: 1,571 tok/s
First token (1K prompt): 0.7 s
Largest safe context: 4K

Best app to run it on the Intel Core Ultra 200V (Arc 140V) (16 GB)

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

Supports Intel Arc through SYCL and Vulkan.
Usually the first to support new model architectures.

llama-server -hf mradermacher/deepseek-moe-16b-chat-i1-GGUF:Q2_K

LM Studio Point-and-click: search, download and chat in one window.
Jan Point-and-click: search, download and chat in one window.

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Supports Intel Arc through SYCL and Vulkan.
Usually the first to support new model architectures.

llama-server -hf mradermacher/deepseek-moe-16b-chat-i1-GGUF:Q2_K

LM Studio Point-and-click: search, download and chat in one window.
Jan Point-and-click: search, download and chat in one window.

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 MoE 16B Chat

Recommended for the Intel Core Ultra 200V (Arc 140V) (16 GB): Q2_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q2_K file (opens in a new tab)

huggingface.co/mradermacher/deepseek-moe-16b-chat-i1-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/deepseek-moe-16b-chat-i1-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/deepseek-moe-16b-chat (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 18Basic quality (D) · 18 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.: How capable the model itself is at Q2_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 Runs welltight fit: How well it runs on the Intel Core Ultra 200V (Arc 140V) (16 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.	8.2 / 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.	24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 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	62.2 / 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 Intel Core Ultra 200V (Arc 140V) (16 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	8.8 GB	9.1 GB	60.8 tok/s	Runs welltight fit	18Basic quality (D) · 18 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.	GGUF (opens in a new tab)
`Q3_K_M`	10.3 GB	9.1 GB	42.2 tok/s	Slowfar over GPU memory limit	21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	12.3 GB	9.1 GB	—	Won't run	24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	13.9 GB	9.1 GB	—	Won't run	25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	15.7 GB	9.1 GB	—	Won't run	25Basic quality (D) · 25 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	19.6 GB	9.1 GB	—	Won't run	26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`F16`	35.0 GB	9.1 GB	—	Won't run	26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 3/100 (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

26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q8_0 · 108 tok/s · Runs great
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 116 tok/s · Runs great
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 121 tok/s · Runs great
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q8_0 · 159 tok/s · Runs great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q4_K_M · 133 tok/s · Runs great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) Q4_K_M · 76.5 tok/s · Runs great

Quick answers

How much memory does DeepSeek MoE 16B Chat need on the Intel Core Ultra 200V (Arc 140V) 16GB?

At Q2_K it needs about 8.8 GB. The Intel Core Ultra 200V (Arc 140V) 16GB has 9.1 GB usable.

How fast is DeepSeek MoE 16B Chat on the Intel Core Ultra 200V (Arc 140V) 16GB?

About 60.8 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek MoE 16B Chat should I use on the Intel Core Ultra 200V (Arc 140V) 16GB?

Q2_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.