What AI models can the Intel Arc B580 run?

VRAM: 12.0 GB
Usable for models: 12.0 GB
Memory bandwidth: 456 GB/s
FP16 compute: 27.3 TFLOPS
Released: 2024
Launch price: $249

478 / 622 LLMs run Best: K2 Horizon 7B 54 / 61 Image models run Best: FLUX.2 [klein] 4B 14 / 43 Video models run Best: LTX-Video 2B 68 / 70 Decision models run Best: Jina Reranker v3.5

More about this hardware

Maker	Intel
Type	Graphics card
Interface	PCIe 4.0

Apps that run models well on the Intel Arc B580

Windows

Linux

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

4 products with the Intel Arc B580

Intel Arc B580 Limited EditionIntel · Graphics card · 12 GB · $249Product page (opens in a new tab)
ASRock Intel Arc B580 Steel Legend 12GB OCASRock · Graphics card · 12 GB · $269Product page (opens in a new tab)
SPARKLE Intel Arc B580 TITAN OCSPARKLE · Graphics card · 12 GB · $269Product page (opens in a new tab)
MAXSUN Intel Arc B580 iCraft 12GMAXSUN · Graphics card · 12 GB · $249 reference MSRPProduct page (opens in a new tab)

Best LLMs for the Intel Arc B580

Quality	Model	Quant	Memory	Speed	Runs
77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	K2 Horizon 7BInstitute of Foundation Models	`Q5_K_M`	8.8 GB	39.2 tok/s	Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 12BGoogle	`Q4_K_M`	9.2 GB	35.8 tok/s	Runs great
75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	MiMo V2.6 Distill Qwen 9BXiaomi	`Q5_K_M`	8.1 GB	37.5 tok/s	Runs great
75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	SenseNova Loop 9B PreviewSenseTime	`Q5_K_M`	8.5 GB	36.6 tok/s	Runs great
74Great quality (A) · 74 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Ornith 1.5 9BDeepReinforce	`Q5_K_M`	8.3 GB	36.6 tok/s	Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 9BAlibaba	`Q5_K_M`	8.3 GB	36.6 tok/s	Runs great
71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	TMax 9BAi2	`Q5_K_M`	7.8 GB	39.5 tok/s	Runs great
72Great quality (A) · 72 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Ornith 1.0 9BDeepReinforce	`Q5_K_M`	8.3 GB	36.6 tok/s	Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt E4BNVIDIA	`Q8_0`	9.8 GB	48.4 tok/s	Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E4BGoogle	`Q8_0`	9.8 GB	48.4 tok/s	Runs great
67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q5_K_M`	9.9 GB	94.5 tok/s	Runs great
67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	UI-Mate 9BTencent	`Q5_K_M`	8.1 GB	37.5 tok/s	Runs great

Best Image models for the Intel Arc B580

Quality	Model	Quant	Memory	Speed	Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`FP8`	10.2 GB	3.7 s	Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`Q4 GGUF`	10.1 GB	12 s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`Q4 GGUF`	10.2 GB	28 s	Runs well
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE-Image TurboBaidu	`Q4 GGUF`	11.3 GB	16 s	Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 9BBlack Forest Labs	`Q4 GGUF`	8.0 GB	9.4 s	Runs greatencoder in RAM
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	DreamShaper XL v2 TurboLykon	`FP16`	8.9 GB	5.4 s	Runs great

Best Video models for the Intel Arc B580

Quality	Model	Quant	Memory	Speed	Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP8`	10.8 GB	1.5 min	Runs welltight fit
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 2BZhipu AI	`FP8`	11.0 GB	3.7 min	Runs welltight fit
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5BZhipu AI	`FP8`	9.6 GB	11.7 min	Runs wellencoder in RAM
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5B I2VZhipu AI	`FP8`	10.2 GB	11.7 min	Runs wellencoder in RAM
55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 T2V 1.3BAlibaba	`FP16`	8.4 GB	17.3 min	Slowencoder in RAM

Best Decision models for the Intel Arc B580

Quality	Model	Quant	Memory	Speed	Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`F16`	2.6 GB	30 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`F16`	2.6 GB	30 ms	Runs great
84Great quality (A) · 84 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.	Intern-Decision 4BShanghai AI Lab	`Q8_0`	6.1 GB	102 ms	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.	Qwen3 Reranker 4BAlibaba	`Q8_0`	5.8 GB	160 ms	Runs well
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	d1 3BLiquid AI	`F16`	7.5 GB	88 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	mxbai-rerank-large v2Mixedbread	`F16`	4.3 GB	72 ms	Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	zerank-2ZeroEntropy	`Q8_0`	5.8 GB	160 ms	Runs well
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	FRIDA-DecisionsSber AI	`F16`	2.4 GB	21 ms	Runs great

Best LLMs by task on this hardware Open in Model Finder

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.