Flint (40B-A2.5B) on NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Can the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB) run Flint (40B-A2.5B)?

Yes, but slowly (far over GPU memory limit)

Slow (far over GPU memory limit). At Q2_K it needs about 18.0 GB of 16.0 GB usable, with an estimated speed of 117 tok/s.

Best quant: Q2_K
Generation speed: 117 tok/s
Prompt processing: 6,912 tok/s
First token (1K prompt): 0.3 s
Largest safe context: —

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

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 Flint (40B-A2.5B) in LM Studio

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

Want an agent? Flint (40B-A2.5B) supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 Flint (40B-A2.5B)

Recommended for the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB): Q2_K. 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 flint:40b

Quantized files · GGUF

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

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

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

ollama run hf.co/unsloth/flint-GGUF:UD-Q2_K_XL

Original weights · Hugging Face

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

huggingface.co/RecursiveSI/flint (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/recursive-oss/rec (opens in a new tab)

Recursive's own local inference engine, linked from the model card.

git clone https://github.com/recursive-oss/rec

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

How it’s rated

Quality 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (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 Slowfar over GPU memory limit: 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.	28.4 / 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.	4.0 / 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	62.4 / 100

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

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

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	18.0 GB	16.0 GB	117 tok/s	Slowfar over GPU memory limit	63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	21.6 GB	16.0 GB	—	Won't run	75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q3_K_XL) (opens in a new tab)
`Q4_K_M`	26.4 GB	16.0 GB	—	Won't run	85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q4_K_XL) (opens in a new tab)
`Q5_K_M`	30.4 GB	16.0 GB	—	Won't run	87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q5_K_XL) (opens in a new tab)
`Q6_K`	34.7 GB	16.0 GB	—	Won't run	89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q6_K_XL) (opens in a new tab)
`Q8_0`	44.3 GB	16.0 GB	—	Won't run	90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	81.7 GB	16.0 GB	—	Won't run	90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab) 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

90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) F16 · 58.9 tok/s · Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Apple M1 Max (64 GB) Q6_K · 82.4 tok/s · Runs great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q6_K · 102 tok/s · Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Pro (48 GB) Q4_K_M · 83.1 tok/s · Runs great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q4_K_M · 222 tok/s · Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. AMD Ryzen AI Max+ 395 (128 GB) Q8_0 · 45.6 tok/s · Runs great

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.