on

Can the NVIDIA RTX PRO 2000 Blackwell Generation Laptop GPU run Phi-3.5 MoE (42B-A6.6B)?

47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.

Yes, but slowly (heavy RAM offload)

Slow (heavy RAM offload). At Q3_K_M it needs about 22.6 GB of 8.0 GB usable, with an estimated speed of 19.9 tok/s.

Best quant
Q3_K_M
Generation speed
19.9 tok/s
Prompt processing
970 tok/s
First token (1K prompt)
1.1 s
Largest safe context
—

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

On Windows

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 Phi-3.5 MoE (42B-A6.6B) in LM Studio

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

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 Phi-3.5 MoE (42B-A6.6B) in LM Studio

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

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 Phi-3.5 MoE (42B-A6.6B)

Recommended for the NVIDIA RTX PRO 2000 Blackwell Generation Laptop GPU: Q3_K_M. 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 Q3_K_M (Q3_K_L) file (opens in a new tab)

huggingface.co/lmstudio-community/Phi-3.5-MoE-instruct-GGUF (opens in a new tab)

ollama run hf.co/lmstudio-community/Phi-3.5-MoE-instruct-GGUF:Q3_K_L

Original weights · Hugging Face

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

huggingface.co/microsoft/Phi-3.5-MoE-instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/microsoft/PhiCookBook (opens in a new tab)

Microsoft’s official Phi cookbook: setup, inference and fine-tuning guides.

git clone https://github.com/microsoft/PhiCookBook

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

How it’s rated

Quality 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (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 Slowheavy RAM offload
How well it runs on the NVIDIA RTX PRO 2000 Blackwell Generation Laptop GPU: 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.21.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.4.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.10.6 / 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 score50.7 / 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 Generation Laptop GPU

Quant Memory needed Available Speed Runs Quality Download
Q2_K 18.8 GB 8.0 GB 26.7 tok/s Slowheavy RAM offload 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q3_K_M 22.6 GB 8.0 GB 19.9 tok/s Slowheavy RAM offload 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. GGUF (Q3_K_L) (opens in a new tab)
Q4_K_M 27.6 GB 8.0 GB — Won't run 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 31.8 GB 8.0 GB — Won't run 54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. GGUF files (opens in a new tab)
Q6_K 36.4 GB 8.0 GB — Won't run 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 46.5 GB 8.0 GB — Won't run 56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 85.8 GB 8.0 GB — Won't run 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 7/100 (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

Quick answers

How much memory does Phi-3.5 MoE (42B-A6.6B) need on the NVIDIA RTX PRO 2000 Blackwell Generation Laptop GPU 8GB?

At Q3_K_M it needs about 22.6 GB. The NVIDIA RTX PRO 2000 Blackwell Generation Laptop GPU 8GB has 8.0 GB usable.

How fast is Phi-3.5 MoE (42B-A6.6B) on the NVIDIA RTX PRO 2000 Blackwell Generation Laptop GPU 8GB?

About 19.9 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Phi-3.5 MoE (42B-A6.6B) should I use on the NVIDIA RTX PRO 2000 Blackwell Generation Laptop GPU 8GB?

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.

Was this page helpful?