DeepSeek Coder V2 (236B) on NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)

Can the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) run DeepSeek Coder V2 (236B)?

Yes, it runs well (over GPU memory limit)

Runs well (over GPU memory limit). At Q2_K it needs about 104 GB of 102 GB usable, with an estimated speed of 22.5 tok/s.

Best quant: Q2_K
Generation speed: 22.5 tok/s
Prompt processing: 987 tok/s
First token (1K prompt): 1.0 s
Largest safe context: —

Best app to run it on the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)

On Linux

LM Studio

Desktop app · runs on llama.cpp, MLX

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open DeepSeek Coder V2 (236B) in LM Studio

Ollama Splits the model between GPU memory and system RAM, which this setup needs.
llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.

Want an agent? DeepSeek Coder V2 (236B) 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 Coder V2 (236B)

Recommended for the NVIDIA RTX Spark N1X (6144-core GPU) (128 GB): Q2_K. 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-v2:236b-instruct-q2_K

Quantized files · GGUF

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

huggingface.co/lmstudio-community/DeepSeek-Coder-V2-Instruct-0724-GGUF (opens in a new tab)

ollama run hf.co/lmstudio-community/DeepSeek-Coder-V2-Instruct-0724-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 (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-V2 (opens in a new tab)

git clone https://github.com/deepseek-ai/DeepSeek-Coder-V2

Links checked 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 51Fair quality (C) · 51 of 100: how capable the model is at Q2_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 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 wellover GPU memory limit: How well it runs on the NVIDIA RTX Spark N1X (6144-core GPU) (128 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.	23.3 / 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.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	11.2 / 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	59.5 / 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 NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	104 GB	102 GB	22.5 tok/s	Runs wellover GPU memory limit	51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.
`Q3_K_M`	125 GB	102 GB	—	Won't run	62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (Q3_K_L) · part 1 of 4 (opens in a new tab)
`Q4_K_M`	153 GB	102 GB	—	Won't run	70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 4 (opens in a new tab)
`Q5_K_M`	177 GB	102 GB	—	Won't run	71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.
`Q6_K`	203 GB	102 GB	—	Won't run	73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · part 1 of 5 (opens in a new tab)
`Q8_0`	259 GB	102 GB	—	Won't run	74Great quality (A) · 74 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 · part 1 of 7 (opens in a new tab)
`F16`	481 GB	102 GB	—	Won't run	74Great quality (A) · 74 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

70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q4_K_M · 36.2 tok/s · Runs great
62Good quality (B) · 62 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. Apple M2 Ultra (192 GB) Q3_K_M · 44.5 tok/s · Runs well (tight fit)
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 36.2 tok/s · Runs great
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) Q2_K · 24.2 tok/s · Runs well (tight fit)
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (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)
51Fair quality (C) · 51 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. Apple M4 Max (128 GB) Q2_K · 33.6 tok/s · Runs well (over GPU memory limit)

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.