DeepSeek V2 Lite Chat on NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition

Can the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition run DeepSeek V2 Lite Chat?

Yes, it runs great

Runs great. At F16 it needs about 37.1 GB of 96.0 GB usable, with an estimated speed of 111 tok/s.

Best quant: F16
Generation speed: 111 tok/s
Prompt processing: 33,000 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 160K

Best app to run it on the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition

On Windows

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-v2:16b-lite-chat-fp16

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

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-v2:16b-lite-chat-fp16

vLLM The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
LM Studio 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 V2 Lite Chat

Recommended for the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition: F16. 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-v2:16b-lite-chat-fp16

Quantized files · GGUF

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

huggingface.co/mradermacher/DeepSeek-V2-Lite-Chat-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/DeepSeek-V2-Lite-Chat-GGUF

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/DeepSeek-V2-Lite-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 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, 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 NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition: 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.	18.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 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.	8.9 / 15
Match score	66.9 / 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 NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	11.9 GB	96.0 GB	264 tok/s	Runs great	28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	13.4 GB	96.0 GB	245 tok/s	Runs great	33Basic quality (D) · 33 of 100: how capable the model is at Q3_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)
`Q4_K_M`	15.2 GB	96.0 GB	224 tok/s	Runs great	38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	16.8 GB	96.0 GB	207 tok/s	Runs great	38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	18.5 GB	96.0 GB	193 tok/s	Runs great	39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	22.3 GB	96.0 GB	168 tok/s	Runs great	40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	37.1 GB	96.0 GB	111 tok/s	Runs great	40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (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

40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q8_0 · 118 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) F16 · 45.3 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 126 tok/s · Runs great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 131 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q5_K_M · 128 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (24 GB) Q5_K_M · 73.7 tok/s · Runs great

Quick answers

How much memory does DeepSeek V2 Lite Chat need on the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 96GB?

At F16 it needs about 37.1 GB. The NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 96GB has 96.0 GB usable.

How fast is DeepSeek V2 Lite Chat on the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 96GB?

About 111 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek V2 Lite Chat should I use on the NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition 96GB?

F16. 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.