MAXSUN Intel Arc B570 Milestone 10G

Specifications

Maker	MAMAXSUN
Type	Graphics card
GPU	Intel Arc B570
Video memory (VRAM)	10.0 GB
Usable for AI models	10.0 GB
Memory bandwidth	380 GB/s
FP16 compute	23.0 TFLOPS
Notes	Boost 2750 MHz; 241 mm
Product page	www.maxsun.com (opens in a new tab)

Cards built on the same GPU with the same memory run AI models at practically the same speed; factory overclocks and coolers change results by only a few percent.

Best LLMs for the MAXSUN Intel Arc B570 Milestone 10G

Quality	Model	Quant	Memory	Speed	Runs
A76Great quality (A) · 76 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.	IOK2 Horizon 7BInstitute of Foundation Models	Q4_K_M	7.8 GB	39.6 tok/s	Runs great
A74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	XMiMo V2.6 Distill Qwen 9BXiaomi	Q4_K_M	7.1 GB	37.9 tok/s	Runs great
A74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	STSenseNova Loop 9B PreviewSenseTime	Q4_K_M	7.5 GB	36.9 tok/s	Runs great
A78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 12BGoogle	Q4_K_M	9.1 GB	29.8 tok/s	Runs welltight fit
A73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	DROrnith 1.5 9BDeepReinforce	Q4_K_M	7.3 GB	36.9 tok/s	Runs great
A72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 9BAlibaba	Q4_K_M	7.3 GB	36.9 tok/s	Runs great
A70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	ATMax 9BAi2	Q4_K_M	6.8 GB	39.8 tok/s	Runs great
A71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	DROrnith 1.0 9BDeepReinforce	Q4_K_M	7.3 GB	36.9 tok/s	Runs great
B69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt E4BNVIDIA	Q6_K	7.8 GB	54.9 tok/s	Runs great
B68Good 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.	BZNanbeige4.2 3BBOSS Zhipin (Nanbeige)	Q8_0	7.0 GB	43.5 tok/s	Runs great

Best Image models for the MAXSUN Intel Arc B570 Milestone 10G

Quality	Model	Quant	Memory	Speed	Runs
A72Great quality (A) · 72 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.	BFFLUX.2 [klein] 4BBlack Forest Labs	Q4 GGUF	8.6 GB	5.6 s	Runs welltight fit
A78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [klein] 9BBlack Forest Labs	Q4 GGUF	8.0 GB	11 s	Runs greatencoder in RAM
A+89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX 3 Image KleinBlack Forest Labs	FP8	7.9 GB	25 s	Runs wellencoder in RAM
A82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	FP8	8.5 GB	11 s	Runs welltight fit · encoder in RAM
A79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	BERNIE-Image TurboBaidu	Q4 GGUF	7.4 GB	19 s	Runs wellencoder in RAM
B56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	LDreamShaper XL v2 TurboLykon	FP8	5.6 GB	5.5 s	Runs great

Best Video models for the MAXSUN Intel Arc B570 Milestone 10G

Quality	Model	Quant	Memory	Speed	Runs
C50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-Video 2BLightricks	FP16	8.0 GB	2.1 min	Runs greatencoder in RAM
D35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	SAAnimateDiff v3 (SD 1.5)Shanghai AI Lab	FP16	4.7 GB	1.6 min	Runs great
C44Fair quality (C) · 44 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.	ZACogVideoX 2BZhipu AI	FP8	6.2 GB	4.4 min	Runs wellencoder in RAM
B55Good 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	19.7 min	Slowencoder in RAM
C53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 VACE 1.3BAlibaba	FP8	8.0 GB	19.2 min	Slowencoder in RAM

Best Decision models for the MAXSUN Intel Arc B570 Milestone 10G

Quality	Model	Quant	Memory	Speed	Runs
A+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.	JAJina Reranker v3.5Jina AI	F16	2.5 GB	35 ms	Runs great
A84Great 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.	JAJina Reranker v3Jina AI	F16	2.5 GB	35 ms	Runs great
A82Great quality (A) · 82 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.	LAd1 3BLiquid AI	Q8_0	4.4 GB	84 ms	Runs great
A82Great 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.	Mmxbai-rerank-large v2Mixedbread	F16	4.2 GB	85 ms	Runs great
A83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	SAIntern-Decision 4BShanghai AI Lab	Q6_K	4.9 GB	114 ms	Runs great
A+90Excellent quality (A+) · 90 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.	Qwen3 Reranker 4BAlibaba	Q8_0	5.7 GB	189 ms	Runs well
A80Great 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.	SAFRIDA-DecisionsSber AI	F16	2.4 GB	25 ms	Runs great
A80Great 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.	FGLiNER2.5 DecideFastino	F16	1.7 GB	16 ms	Runs great

Other products with the Intel Arc B570

• ASRock Intel Arc B570 Challenger 10GB OCASASRock · Graphics card · 10 GB · $219Product page (opens in a new tab)
• SPARKLE Intel Arc B570 GUARDIAN OCSPSPARKLE · Graphics card · 10 GB · $230Product page (opens in a new tab)