What AI models can the NVIDIA T4 run?

VRAM: 16.0 GB
Usable for models: 16.0 GB
Memory bandwidth: 320 GB/s
FP16 compute: 16.2 TFLOPS
Released: 2018

491 / 622 LLMs run Best: Gemma 4 26B-A4B 55 / 61 Image models run Best: Z-Image Turbo 17 / 43 Video models run Best: LTX-Video 2B 68 / 70 Decision models run Best: Jina Reranker v3.5

More about this hardware

Maker	NVIDIA
Type	Workstation / datacenter graphics card
Interface	PCIe 3.0

Apps that run models well on the NVIDIA T4

Linux

vLLMThe full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
OllamaOne command with Ollama’s own build of this model.
LM StudioPoint-and-click: search, download and chat in one window.
SGLangThe full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Windows

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

Best LLMs for the NVIDIA T4

Quality	Model	Quant	Memory	Speed	Runs
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 26B-A4BGoogle	`Q3_K_M`	14.4 GB	93.3 tok/s	Runs welltight fit
78Great 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`	9.4 GB	32.8 tok/s	Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Raon-1 mini Preview (30B-A4B)KRAFTON	`Q3_K_M`	15.6 GB	85.4 tok/s	Runs welltight fit
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	gpt-oss 20BOpenAI	`MXFP4`	13.5 GB	83.8 tok/s	Runs great
69Good 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.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q6_K`	11.5 GB	78.2 tok/s	Runs great
70Great quality (A) · 70 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.	Nemotron 3.5 Bolt E4BNVIDIA	`Q8_0`	10.0 GB	44.4 tok/s	Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	K2 Horizon 7BInstitute of Foundation Models	`Q4_K_M`	8.1 GB	43.6 tok/s	Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.8 27BAlibaba	`Q3_K_M`	15.5 GB	18.3 tok/s	Runs welltight fit
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`	10.0 GB	44.4 tok/s	Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 27BAlibaba	`Q3_K_M`	15.5 GB	18.3 tok/s	Runs welltight fit
67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Maple Preview (20B-A1B)DeepGrove	`Q5_K_M`	15.9 GB	124 tok/s	Runs welltight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	SenseNova Loop 9B PreviewSenseTime	`Q4_K_M`	7.8 GB	40.7 tok/s	Runs great

Best Image models for the NVIDIA T4

Quality	Model	Quant	Memory	Speed	Runs
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`Q8 GGUF`	13.0 GB	9.8 s	Runs great
89Excellent quality (A+) · 89 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.	FLUX 3 Image KleinBlack Forest Labs	`FP8`	12.4 GB	17 s	Runs well
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE-Image TurboBaidu	`FP8`	14.5 GB	9.8 s	Runs welltight fit
77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`Q8 GGUF`	10.5 GB	3.9 s	Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 9BBlack Forest Labs	`Q8 GGUF`	12.3 GB	7.4 s	Runs greatencoder in RAM
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Z-ImageAlibaba (Tongyi)	`FP8`	12.6 GB	52 s	Slow

Best Video models for the NVIDIA T4

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 77/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP8`	10.8 GB	76 s	Runs great
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 2BZhipu AI	`FP8`	11.0 GB	3.1 min	Runs great
53Fair quality (C) · 53 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.	Wan 2.1 T2V 1.3BAlibaba	`FP8`	12.8 GB	12.2 min	Slow
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5BZhipu AI	`FP8`	14.3 GB	9.2 min	Runs welltight fit
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5B I2VZhipu AI	`FP8`	14.9 GB	9.2 min	Runs welltight fit

Best Decision models for the NVIDIA T4

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`	2.8 GB	37 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`	2.8 GB	37 ms	Runs great
82Great 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.	d1 3BLiquid AI	`Q8_0`	4.7 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`	4.5 GB	88 ms	Runs great
84Great quality (A) · 84 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.	Intern-Decision 4BShanghai AI Lab	`Q8_0`	6.3 GB	126 ms	Runs great
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`	6.0 GB	201 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	26 ms	Runs great
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.	GLiNER2.5 DecideFastino	`F16`	1.7 GB	17 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.