FLUX.2 [klein] 9B on NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Can the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB) run FLUX.2 [klein] 9B?

Yes, it runs great (encoder unloaded after use)

Runs great (encoder unloaded after use). At Q8 GGUF it needs about 12.3 GB of 16.0 GB usable, with an estimated speed of 5.5 s.

Best precision: Q8 GGUF
Memory mode: Text encoder offloaded
Time per image: 5.5 s
Output: 1024×1024, 4 steps

Best app to run it on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

On Linux

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

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 FLUX.2 [klein] 9B

Recommended for the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB): q8_gguf. Every other precision has its own download link in the table below.

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

Download the q8_gguf (Q8_0) file (opens in a new tab)

huggingface.co/unsloth/FLUX.2-klein-9B-GGUF (opens in a new tab)

Original weights · Hugging Face

Full-precision files from Black Forest Labs, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/black-forest-labs/FLUX.2-klein-9B (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Official repo · GitHub

Reference code, inference scripts and docs from Black Forest Labs. The weights themselves download from Hugging Face.

github.com/black-forest-labs/flux2 (opens in a new tab)

git clone https://github.com/black-forest-labs/flux2

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

How it’s rated

Quality 83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8 GGUF, 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 greatencoder unloaded after use: How well it runs on the NVIDIA RTX Spark N1X (5120-core GPU) (32 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.	37.4 / 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.	20.0 / 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	87.4 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every precision on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	8.8 GB	16.0 GB	5.9 s	Sequential CPU offload	Runs greatCPU offload	84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	11.7 GB	16.0 GB	4.3 s	Text encoder offloaded	Runs greatencoder unloaded after use	82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q8 GGUF`	12.3 GB	16.0 GB	5.5 s	Text encoder offloaded	Runs greatencoder unloaded after use	83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4 GGUF`	8.0 GB	16.0 GB	5.7 s	Text encoder offloaded	Runs greatencoder unloaded after use	78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)

Other hardware that runs it

84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) FP16 · 11 s · Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q8 GGUF · 1.7 s · Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX FP8 · 1.8 s · Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 FP8 · 3.0 s · Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 FP8 · 1.6 s · Runs great
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) FP16 · 16 s · Runs well

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.