Spark X2.6 1.7B on Apple M3 Ultra (512 GB)

Can the Apple M3 Ultra (512 GB) run Spark X2.6 1.7B?

Yes, it runs great

Runs great. At F16 it needs about 34.9 GB of 384 GB usable, with an estimated speed of 119 tok/s.

Best quant: F16
Generation speed: 119 tok/s
Prompt processing: 10,297 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 1,024K

Best app to run it on the Apple M3 Ultra (512 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX

Point-and-click: search, download and chat in one window.

Open Spark X2.6 1.7B in LM Studio

llama.cpp Usually the first to support new model architectures.
Ollama Runs the Hugging Face GGUF with ollama run hf.co/…

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 Spark X2.6 1.7B

Quantized files · GGUF

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

huggingface.co/XHToken/Spark-X2.6-1.7B-GGUF (opens in a new tab)

ollama run hf.co/XHToken/Spark-X2.6-1.7B-GGUF

Original weights · Hugging Face

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

huggingface.co/XHToken/Spark-X2.6-1.7B (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at F16, 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 Apple M3 Ultra (512 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.	7.2 / 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.	25.0 / 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.	2.1 / 15
Match score	49.3 / 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 Apple M3 Ultra (512 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	32.1 GB	384 GB	831 tok/s	Runs great	11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	32.3 GB	384 GB	654 tok/s	Runs great	13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	32.5 GB	384 GB	506 tok/s	Runs great	15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	32.7 GB	384 GB	418 tok/s	Runs great	15Basic quality (D) · 15 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	32.8 GB	384 GB	351 tok/s	Runs great	15Basic quality (D) · 15 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	33.3 GB	384 GB	258 tok/s	Runs great	16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	34.9 GB	384 GB	119 tok/s	Runs great	16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (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

16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 F16 · 45.8 tok/s · Runs great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 F16 · 58.7 tok/s · Runs great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB F16 · 60.6 tok/s · Runs great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER F16 · 84.9 tok/s · Runs great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 92.8 tok/s · Runs great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Ti 16GB F16 · 48.5 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.