Catalog updated 2026-10-31

Best image models for 8 GB of VRAM

Which open-weight image models run on an NVIDIA GPU with 8 GB of VRAM. Verdicts come from exact Hugging Face file sizes, model card and app maker statements, and published runs.

Run
5
Unknown
0
Fits with offload
3
Exceeds VRAM
2
Answer

5 of 10 listed image models run on an NVIDIA GPU with 8 GB of VRAM: Qwen-Image-2.1, Z-Image-Turbo, FLUX.1 [dev], FLUX 3 Image Klein and SDXL Base 1.0. Highest blind-vote rank among them: Qwen-Image-2.1, #19 of 82 in text to image (Arena, snapshot 2026-10-07). FLUX.2 [klein], MOSS-Image and Stable Diffusion 3.5 Large fit with offload: the main model weights fit in VRAM; the text encoder and VAE run from system RAM, which is slower. FLUX.2 [dev] and Krea 2 Turbo exceed the card even for the main weights.

License check before commercial use: Qwen-Image-2.1, FLUX.1 [dev], FLUX 3 Image Klein.

Table 1

Which image models run on an NVIDIA GPU with 8 GB of VRAM?

10 models

Runs means a model card, app maker or NVIDIA figure, or a dated run on a named card, at or below 8 GB. Fits with offload means the main model weights fit in 8 GB with a 15% margin but the full set does not: the text encoder and VAE run from system RAM, which is slower. Exceeds VRAM means even the main weights are too large for the card. Mac runs never count here. unknown means no source covers this size yet; it is not a failure.

Image models for an NVIDIA GPU with 8 GB of VRAM, with the reason for each verdict
ModelVerdictWhyQualityApp
Qwen-Image-2.1Qwen Research License AgreementRuns · StatedStated by the source: 7 GB of VRAM runs it, below this 8 GB tier (DiffSynth-Studio, weights streamed from disk).DiffSynth-Studio docs: Qwen-Image-2.1#19 of 82 in text to image11,441 votesDiffusers, stable-diffusion.cpp
Z-Image-TurboApache 2.0Runs · StatedStated by the source: 4 GB of VRAM runs it, below this 8 GB tier (stable-diffusion.cpp with GGUF weights).stable-diffusion.cpp Z-Image docs#59 of 82 in text to image24,808 votesDiffusers, stable-diffusion.cpp
FLUX.1 [dev]FLUX.1 [dev] Non-Commercial License v1.1.1Runs · StatedStated by the source: 6 GB of VRAM runs it, below this 8 GB tier (stable-diffusion.cpp with GGUF weights).stable-diffusion.cpp FLUX docs#78 of 82 in text to image49,221 votesDiffusers, ComfyUI
FLUX 3 Image KleinFLUX Kommunity License v1.0Runs · StatedStated by the source: 8 GB of VRAM runs it (official ComfyUI int8 files).FLUX 3 Image Klein README (Black Forest Labs)No independent score yetDiffusers
SDXL Base 1.0CreativeML Open RAIL++-M LicenseRuns · StatedStated by the source: 8 GB of VRAM runs it (SDXL 1.0, no app named).SDXL 1.0 announcement (Stability AI)No independent score yetComfyUI, stable-diffusion.cpp
FLUX.2 [klein]Apache 2.0 (4B), FLUX Non-Commercial License (9B)Fits with offloadThe main model weights of Klein 4B Q8_0 GGUF, 4.3 GB, fit in 8 GB of VRAM with a 15% margin; the full set is 12.5 GB, so the text encoder and VAE run from system RAM, which is slower.No independent score yetDiffusers, stable-diffusion.cpp
MOSS-ImageApache 2.0Fits with offloadThe main model weights of UD-Q4_K_XL GGUF, 3.4 GB, fit in 8 GB of VRAM with a 15% margin; the full set is 13.2 GB, so the text encoder and VAE run from system RAM, which is slower.No independent score yetstable-diffusion.cpp
Stable Diffusion 3.5 LargeStability AI Community LicenseFits with offloadThe main model weights of Q4_0 GGUF, 4.8 GB, fit in 8 GB of VRAM with a 15% margin; the full set is 16.4 GB, so the text encoder and VAE run from system RAM, which is slower.#81 of 82 in text to image23,396 votesComfyUI
FLUX.2 [dev]FLUX Non-Commercial LicenseExceeds VRAMEven the main model weights are too large: the smallest complete download, Q4_K_M GGUF at 34.8 GB, has 20.1 GB of them, more than 8 GB of VRAM holds with a 15% margin.#38 of 82 in text to image77,988 votesDiffusers, ComfyUI, stable-diffusion.cpp
Krea 2 TurboKrea 2 Community License Agreement v.1Exceeds VRAMEven the main model weights are too large: the smallest complete download, Turbo Q4_K_M GGUF at 16.9 GB, has 7.5 GB of them, more than 8 GB of VRAM holds with a 15% margin.No independent score yetDiffusers, stable-diffusion.cpp

Quality: blind human votes from Arena (arena.ai), CC BY 4.0, snapshot 2026-10-07. Scores are for the Arena checkpoint, not your local quantized build.

Frequently asked questions

What is the best image model for an NVIDIA GPU with 8 GB of VRAM?

Qwen-Image-2.1 has the highest blind-vote rank among the image models that run on an NVIDIA GPU with 8 GB of VRAM: #19 of 82 in text to image, from 11,441 votes (Arena, snapshot 2026-10-07). Z-Image-Turbo, FLUX.1 [dev], FLUX 3 Image Klein and SDXL Base 1.0 also run.

Which image models run on an NVIDIA GPU with 8 GB of VRAM?

Qwen-Image-2.1 (7 GB stated by DiffSynth-Studio docs: Qwen-Image-2.1), Z-Image-Turbo (4 GB stated by stable-diffusion.cpp Z-Image docs), FLUX.1 [dev] (6 GB stated by stable-diffusion.cpp FLUX docs), FLUX 3 Image Klein (8 GB stated by FLUX 3 Image Klein README (Black Forest Labs)) and SDXL Base 1.0 (8 GB stated by SDXL 1.0 announcement (Stability AI)).

Which image models fit 8 GB of VRAM only with offload?

FLUX.2 [klein] (Klein 4B Q8_0 GGUF: 4.3 GB of main weights in a 12.5 GB set), MOSS-Image (UD-Q4_K_XL GGUF: 3.4 GB of main weights in a 13.2 GB set) and Stable Diffusion 3.5 Large (Q4_0 GGUF: 4.8 GB of main weights in a 16.4 GB set). The main model weights fit in VRAM; the text encoder and VAE run from system RAM, which is slower.

Which image models exceed 8 GB of VRAM even for the main weights?

FLUX.2 [dev] (Q4_K_M GGUF: 20.1 GB of main weights in a 34.8 GB set) and Krea 2 Turbo (Turbo Q4_K_M GGUF: 7.5 GB of main weights in a 16.9 GB set). Even their main model weights are too large for the card with a 15% margin, so part of the model itself has to sit in system RAM.

Other memory sizes