Exxact TensorEX Rackmount Workstation - TWS-154715021

Configurations

Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.

Specifications 48.0 GB configuration

Maker	EExxact
Type	Workstation
Chip	NVIDIA L40S
Video memory (VRAM)	48.0 GB
Usable for AI models	48.0 GB
Memory bandwidth	864 GB/s
FP16 compute	91.6 TFLOPS
Notes	Workstation with NVIDIA RTX professional graphics; each option below is a GPU you can configure. Listed on the NVIDIA Marketplace.
Product page	www.exxactcorp.com (opens in a new tab)

Best LLMs for the Exxact TensorEX Rackmount Workstation - TWS-154715021 48.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	OBMiniCPM-V 4.7 35B-A3BOpenBMB	Q8_0	40.5 GB	107 tok/s	Runs great
A+92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 35B-A3BAlibaba	Q6_K	32.6 GB	130 tok/s	Runs great
A+92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 35B-A3BAlibaba	Q6_K	32.6 GB	130 tok/s	Runs great
A+92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 26B-A4BGoogle	Q8_0	30.8 GB	92.2 tok/s	Runs great
A+92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	NANex N2 Mini (35B-A3B)Nex-AGI	Q8_0	40.4 GB	107 tok/s	Runs great
A+91Excellent quality (A+) · 91 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	KKAT-Coder V2.5 Dev (35B-A3B)Kuaishou	Q8_0	39.9 GB	107 tok/s	Runs great
A+90Excellent quality (A+) · 90 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.	ISSage-A1.5 35B-A3BInternScience	Q6_K	32.6 GB	130 tok/s	Runs great
A+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.	RFlint (40B-A2.5B)Recursive	Q6_K	35.9 GB	143 tok/s	Runs great
A+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.	DROrnith 1.5 35B-A3BDeepReinforce	Q6_K	32.6 GB	130 tok/s	Runs great
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	AApodex 1.1 Mini (35B-A3B)Apodex	Q6_K	32.6 GB	130 tok/s	Runs great

Best Image models for the Exxact TensorEX Rackmount Workstation - TWS-154715021 48.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	KKrea 2 TurboKrea	FP16	37.4 GB	4.0 s	Runs great
A+87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	Qwen-Image 2.1 TurboAlibaba	FP8	30.8 GB	9.7 s	Runs great
A84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [klein] 9BBlack Forest Labs	FP16	37.1 GB	1.7 s	Runs great
A+91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX 3 Image KleinBlack Forest Labs	FP16	22.4 GB	5.3 s	Runs great
A+91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	MMMiniMax H3 ImageMiniMax	FP8	38.6 GB	8.7 s	Runs greatencoder in RAM
A+85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	BERNIE-Image TurboBaidu	FP16	26.4 GB	3.0 s	Runs great

Best Video models for the Exxact TensorEX Rackmount Workstation - TWS-154715021 48.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-2.5 (22B, video + audio)Lightricks	Q4 GGUF	39.9 GB	1.7 min	Runs great
A84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-2.3Lightricks	FP8	44.3 GB	5.6 min	Runs welltight fit
A80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-2 (19B, video + audio)Lightricks	FP8	44.3 GB	5.6 min	Runs welltight fit
B66Good quality (B) · 66 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.	LLTX-Video 13B 0.9.8 (distilled)Lightricks	FP8	30.1 GB	50 s	Runs great
A84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.2 I2V A14BAlibaba	FP8	38.3 GB	22.2 min	Slow

Best Decision models for the Exxact TensorEX Rackmount Workstation - TWS-154715021 48.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A+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.	Qwen3 Reranker 4BAlibaba	F16	11.3 GB	51 ms	Runs great
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 8BAlibaba	Q8_0	12.0 GB	83 ms	Runs great
A+88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	ZEzerank-2ZeroEntropy	F16	11.3 GB	51 ms	Runs great
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	4.4 GB	11 ms	Runs great
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.	Shieldstral 1.0 3BMistral AI	F16	10.9 GB	49 ms	Runs great
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	SSkywork Reward V2 Llama 3.1 8BSkywork	Q8_0	10.4 GB	131 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.	SAIntern-Decision 4BShanghai AI Lab	F16	12.1 GB	40 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	4.4 GB	11 ms	Runs great