on

Can the NVIDIA RTX PRO 2000 Blackwell run Intern-Decision 4B?

83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At Q6_K it needs about 5.2 GB of 16.0 GB usable and makes one decision in about 117 ms.

Best quant
Q6_K
Time per decision
117 ms
Decisions per second
8.5/s
Input assumed
256 tokens
Returns
Probability or score

Best app to run it on the NVIDIA RTX PRO 2000 Blackwell

On Windows

Sentence Transformers

Python library · runs on PyTorch (Transformers)

  • A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

Get Sentence Transformers

  • Docker Model Runner Handy if you already work in Docker.
  • vLLM For one person, llama.cpp-based apps are about as fast and use smaller GGUF files.

On Linux

Docker Model Runner

Command line + local API · runs on llama.cpp, vLLM

  • Handy if you already work in Docker.
docker model run hf.co/internlm/Intern-Decision-4B
  • vLLM For one person, llama.cpp-based apps are about as fast and use smaller GGUF files.
  • Sentence Transformers A few lines of Python with Transformers or Sentence Transformers; easiest for scripts and notebooks.

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 Intern-Decision 4B

Original weights · Hugging Face

Full-precision files from Shanghai AI Lab, for fine-tuning, vLLM, Transformers.

huggingface.co/internlm/Intern-Decision-4B (opens in a new tab)

No sign-in needed.

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (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 Runs great
How well it runs on the NVIDIA RTX PRO 2000 Blackwell: 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.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.37.4 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.13.8 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.15.0 / 15
Match score91.3 / 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 2000 Blackwell

Quant Memory needed Available Speed Runs Quality Download
Q4_K_M 4.2 GB 16.0 GB 112 ms Runs great 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q5_K_M 4.7 GB 16.0 GB 114 ms Runs great 81Great quality (A) · 81 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q6_K 5.2 GB 16.0 GB 117 ms Runs great 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
Q8_0 6.3 GB 16.0 GB 124 ms Runs great 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. All files (opens in a new tab)
F16 10.5 GB 16.0 GB 154 ms Runs well 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)

Times are for one request with a 256-token input and about 1 tokens written. Batching servers process many requests at once.

Other hardware that runs it

Quick answers

How much memory does Intern-Decision 4B need on the NVIDIA RTX PRO 2000 Blackwell 16GB?

At Q6_K it needs about 5.2 GB. The NVIDIA RTX PRO 2000 Blackwell 16GB has 16.0 GB usable.

How fast is Intern-Decision 4B on the NVIDIA RTX PRO 2000 Blackwell 16GB?

It makes one decision in about 117 ms at Q6_K, an estimate from the hardware and the size of the model.

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?