Spark-X2.6 4B on AMD Radeon PRO W7800 48GB

Can the AMD Radeon PRO W7800 48GB run Spark-X2.6 4B?

Yes, it runs great

Runs great. At F16 it needs about 11.5 GB of 48.0 GB usable, with an estimated speed of 52.1 tok/s.

Best quant: F16
Generation speed: 52.1 tok/s
Prompt processing: 13,637 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 974K

Best app to run it on the AMD Radeon PRO W7800 48GB

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull XHToken/Spark-X2.6-4B-GGUF:F16

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

On Linux

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull XHToken/Spark-X2.6-4B-GGUF:F16

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

Want an agent? Spark-X2.6 4B 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 Spark-X2.6 4B

Quantized files · GGUF

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

huggingface.co/XHToken/Spark-X2.6-4B-GGUF (opens in a new tab)

ollama run hf.co/XHToken/Spark-X2.6-4B-GGUF

Original weights · Hugging Face

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

huggingface.co/XHToken/Spark-X2.6-4B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/XHToken/Spark-X2.6 (opens in a new tab)

SparkLLM's official repo for the Spark-X2.6 open model series.

git clone https://github.com/XHToken/Spark-X2.6

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

How it’s rated

Quality 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (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 AMD Radeon PRO W7800 48GB: 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.	29.7 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	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.	5.5 / 15
Match score	75.2 / 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 AMD Radeon PRO W7800 48GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	4.9 GB	48.0 GB	365 tok/s	Runs great	46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q3_K_M`	5.3 GB	48.0 GB	287 tok/s	Runs great	55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q4_K_M`	5.8 GB	48.0 GB	222 tok/s	Runs great	62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	6.2 GB	48.0 GB	184 tok/s	Runs great	64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q6_K`	6.7 GB	48.0 GB	154 tok/s	Runs great	65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF files (opens in a new tab)
`Q8_0`	7.7 GB	48.0 GB	113 tok/s	Runs great	66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	11.5 GB	48.0 GB	52.1 tok/s	Runs great	66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (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

66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q8_0 · 41.4 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 47.1 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER F16 · 51.6 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti F16 · 62.8 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 F16 · 67.3 tok/s · Runs great
66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q8_0 · 53.0 tok/s · Runs great

Quick answers

How much memory does Spark-X2.6 4B need on the PRO W7800 48GB?

At F16 it needs about 11.5 GB. The PRO W7800 48GB has 48.0 GB usable.

How fast is Spark-X2.6 4B on the PRO W7800 48GB?

About 52.1 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Spark-X2.6 4B should I use on the PRO W7800 48GB?

F16. 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.