Kimi K3 (2.8T) on NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

Can the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB) run Kimi K3 (2.8T)?

No, it doesn’t fit

No. Kimi K3 (2.8T) needs about 1,115 GB even at Q2_K; the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB) has 32.2 GB usable.

Download Kimi K3 (2.8T)

Recommended: Q2_K. Every other quantization has its own download link in the table below.

Ollama

Ollama offers this only as a cloud model (it runs on Ollama’s servers, not your machine). To run it locally, use the GGUF files below.

Quantized files · GGUF

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

Download the Q2_K (UD-Q2_K_XL) files (opens in a new tab)

huggingface.co/unsloth/Kimi-K3-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Kimi-K3-GGUF

Original weights · Hugging Face

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

huggingface.co/moonshotai/Kimi-K3 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/MoonshotAI/Kimi-K3 (opens in a new tab)

git clone https://github.com/MoonshotAI/Kimi-K3

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

How it’s rated

Quality 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (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 Won't run: How well it runs on the NVIDIA RTX Spark N1X (6144-core GPU) (48 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.	9.3 / 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.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Match score	9.3 / 100

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

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Every quantization on the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	1,115 GB	32.2 GB	—	Won't run	68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
`Q3_K_M`	1,366 GB	32.2 GB	—	Won't run	82Great quality (A) · 82 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	1,699 GB	32.2 GB	—	Won't run	93Excellent quality (A+) · 93 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q4_K_XL) · folder (opens in a new tab)
`Q5_K_M`	1,977 GB	32.2 GB	—	Won't run	95Excellent quality (A+) · 95 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	2,283 GB	32.2 GB	—	Won't run	97Excellent quality (A+) · 97 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	2,950 GB	32.2 GB	—	Won't run	98Excellent quality (A+) · 98 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 13/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q8_K_XL) · folder (opens in a new tab)
`F16`	5,563 GB	32.2 GB	—	Won't run	98Excellent quality (A+) · 98 of 100: how capable the model is at F16, whatever it runs on. Match score 13/100 (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.

Hardware that can run it

None. No single GPU or device in our catalog runs this model on its own; it needs several GPUs working together.

Models that do run on the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 26B-A4B Q6_K · 54.1 tok/s
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Nex N2 Mini (35B-A3B) Q6_K · 65.1 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.6 35B-A3B Q4_K_M · 86.9 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM-V 4.7 35B-A3B Q4_K_M · 86.9 tok/s
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. Qwen3.5 35B-A3B Q4_K_M · 86.9 tok/s

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.