FLUX.1 [dev] VRAM requirements
The 12B text-to-image model from Black Forest Labs that most local workflows are built around. Strong prompt following and readable text.
TypeImage
Parameters12B
Fits entirely from7 GB
8-bit or better from15 GB
01Measured on my RTX 5060 Ti 16 GB
FP8 · 1024×1024FASTEST
36.4s / image
flux1-dev-fp8.safetensors
Peak VRAM14.8 GB
Run range36.0–37.1 s
Q8_0 · 1024×1024
40.6s / image
flux1-dev-Q8_0.gguf
Peak VRAM15.1 GB
Run range40.5–40.7 s
Q4_K_S · 1024×1024
47.3s / image
flux1-dev-Q4_K_S.gguf
Peak VRAM8.8 GB
Run range47.2–47.4 s
⟷
FP8 · 36.4 sGGUF Q8_0 · 40.6 sSame seed, same prompt
FP8 or GGUF Q8_0: can you see the difference?
Drag the handle. Both images came out of the same workflow on my RTX 5060 Ti 16 GB; only the model file changed.
FP8 workflow GGUF Q8_0 workflow02The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 23.8 GB | 26.1 GB | 27 GB | the original weights | black-forest-labs/FLUX.1-dev → |
| Q8_0 | 12.7 GB | 15.0 GB | 16 GB | practically identical to the original | city96/FLUX.1-dev-gguf → |
| FP8 | 11.9 GB | 14.2 GB | 15 GB | practically identical to the original | Kijai/flux-fp8 → |
| Q6_K | 9.9 GB | 12.2 GB | 13 GB | very close to the original | city96/FLUX.1-dev-gguf → |
| Q5_K_S | 8.3 GB | 10.6 GB | 11 GB | close; small differences in fine detail | city96/FLUX.1-dev-gguf → |
| Q4_K_S | 6.8 GB | 9.1 GB | 10 GB | good; some loss in fine detail and text | city96/FLUX.1-dev-gguf → |
| Q3_K_S | 5.2 GB | 7.5 GB | 8 GB | noticeable loss of detail | city96/FLUX.1-dev-gguf → |
| Q2_K | 4.0 GB | 6.3 GB | 7 GB | heavy loss; a last resort | city96/FLUX.1-dev-gguf → |
“Needed” = file + 1.5 GB working memory + 0.8 GB system reserve.
Free ComfyUI workflow, tested on my RTX 5060 Ti: FP8 workflow (.json) · GGUF Q8_0 workflow (.json). Drag the file into ComfyUI. All workflows →
03By amount of VRAM
04Best GPU for FLUX.1 dev
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for FLUX.1 dev → Planning bigger images or longer clips? Open the calculator →
05By graphics card
| GPU | VRAM | Verdict | Best file | Needed |
|---|---|---|---|---|
| Desktop graphics cards | ||||
| RTX 2060 6 GB | 6 GB | Offload only | Q3_K_S | 7.5 GB |
| RTX 3050 6 GB | 6 GB | Offload only | Q3_K_S | 7.5 GB |
| RTX 2070 Super 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 2080 Super 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 3050 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 3060 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 3060 Ti 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 3070 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 3070 Ti 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 4060 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 4060 Ti 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 5050 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 5060 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 5060 Ti 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RX 7600 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RX 9050 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RX 9060 XT 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| Arc B570 10 GB | 10 GB | Runs | Q4_K_S | 9.1 GB |
| RTX 3080 10 GB | 10 GB | Runs | Q4_K_S | 9.1 GB |
| RTX 2080 Ti 11 GB | 11 GB | Runs | Q5_K_S | 10.6 GB |
| Arc B580 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 2060 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 3060 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 3080 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 3080 Ti 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 4070 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 4070 Super 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 4070 Ti 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 5070 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RX 7700 XT 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RX 9070 GRE 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| Arc A770 16 GB | 16 GB | Runs well | Q8_0 | 15.0 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RTX 4080 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RTX 5080 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RX 7600 XT 16 GB | 16 GB | Runs well | Q8_0 | 15.0 GB |
| RX 7800 XT 16 GB | 16 GB | Runs well | Q8_0 | 15.0 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs well | Q8_0 | 15.0 GB |
| RX 9060 XT 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RX 9070 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RX 9070 XT 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | Q8_0 | 15.0 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | Q8_0 | 15.0 GB |
| RTX 3090 24 GB | 24 GB | Runs well | Q8_0 | 15.0 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | Q8_0 | 15.0 GB |
| RTX 4090 24 GB | 24 GB | Runs well | FP8 | 14.2 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | Q8_0 | 15.0 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | 16-bit | 26.1 GB |
| RTX 5090 32 GB | 32 GB | Runs well | 16-bit | 26.1 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Offload only | Q4_K_S | 9.1 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Offload only | Q4_K_S | 9.1 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Offload only | Q3_K_S | 7.5 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Offload only | Q3_K_S | 7.5 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Offload only | Q3_K_S | 7.5 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Offload only | Q3_K_S | 7.5 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RX 7600M 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RX 7600M XT 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RX 7600S 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RX 7700S 8 GB | 8 GB | Tight | Q3_K_S | 7.5 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RX 7800M 12 GB | 12 GB | Runs | Q5_K_S | 10.6 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs well | Q8_0 | 15.0 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs well | Q8_0 | 15.0 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs well | FP8 | 14.2 GB |
| RX 7900M 16 GB | 16 GB | Runs well | Q8_0 | 15.0 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | FP8 | 14.2 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 26.1 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 26.1 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Runs | Q6_K | 12.2 GB |
| Mac 18 GB | 14.4 GB | Runs | Q6_K | 12.2 GB |
| Mac 24 GB | 19.6 GB | Runs well | Q8_0 | 15.0 GB |
| Mac 32 GB | 26.8 GB | Runs well | 16-bit | 26.1 GB |
| Mac 36 GB | 30.2 GB | Runs well | 16-bit | 26.1 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 26.1 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 26.1 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 26.1 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 26.1 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 26.1 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 26.1 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 26.1 GB |
06Text encoder, VAE and other files
| File | Folder | Size | When | |
|---|---|---|---|---|
| CLIP-L clip_l.safetensors | models/text_encoders | 0.2 GB | required | Download → |
| T5-XXL FP8 t5xxl_fp8_e4m3fn.safetensors | models/text_encoders | 4.9 GB | text encoder · smaller, recommended | Download → |
| T5-XXL FP16 t5xxl_fp16.safetensors | models/text_encoders | 9.8 GB | text encoder · alternative | Download → |
| FLUX.1 VAE (ae) ae.safetensors | models/vae | 0.3 GB | required | Download → |
The files the official ComfyUI workflows load next to the model. Sizes read from Hugging Face (2026-10-01).
07Where the files go in ComfyUI
| File | Folder | Loader node |
|---|---|---|
| Diffusion model (.safetensors: 16-bit, FP8, INT8) | ComfyUI/models/diffusion_models | Load Diffusion Model |
| GGUF file (.gguf) | ComfyUI/models/unet | Unet Loader (GGUF) - from the ComfyUI-GGUF node pack |
| Text encoder | ComfyUI/models/text_encoders | Load CLIP / DualCLIPLoader (or the GGUF versions) |
| VAE | ComfyUI/models/vae | Load VAE |
08Measured and reported results
| Label | GPU | Setup | Result | Peak VRAM | Date | Source |
|---|---|---|---|---|---|---|
| measured | RTX 5060 Ti 16 GB | flux1-dev-Q8_0.gguf · 1024x1024 · 20 steps 3 timed runs after 1 warm-up (50.7 s incl. loading). T5-XXL FP8 + CLIP-L, euler/simple, guidance 3.5, ComfyUI 0.25.0 portable, PyTorch 2.12 cu130, 32 GB RAM. Time = sampling + VAE | 40.62 s / image | 15.1 GB | 2026-09-27 | |
| measured | RTX 5060 Ti 16 GB | flux1-dev-Q4_K_S.gguf · 1024x1024 · 20 steps 3 timed runs after 1 warm-up (52.1 s incl. loading). T5-XXL FP8 + CLIP-L, euler/simple, guidance 3.5, ComfyUI 0.25.0 portable, PyTorch 2.12 cu130, 32 GB RAM. Time = sampling + VAE | 47.28 s / image | 8.8 GB | 2026-09-27 | |
| measured | RTX 5060 Ti 16 GB | flux1-dev-fp8.safetensors · 1024x1024 · 20 steps 3 timed runs after 1 warm-up (39.1 s incl. loading). T5-XXL FP8 + CLIP-L, euler/simple, guidance 3.5, ComfyUI 0.25.0 portable, PyTorch 2.12 cu130, 32 GB RAM. Time = sampling + VAE | 36.36 s / image | 14.8 GB | 2026-09-27 | |
| reported | Arc A770 16 GB | fp8 (ComfyUI template) · 20 steps “20/20 [00:46<00:00, 2.33s/it] Prompt executed in 47.13 seconds” 'GPU Benchmark Flux DEV fp8' thread; Intel A770 on Fedora Linux, PyTorch 2.3.110+xpu (53.26 s with PyTorch nightly); resolution not stated | 47.13 s / image · 2.33 s/it | — | 2025-07-24 | github.com → |
| reported | Arc B580 12 GB | fp8 · 1024x1024 · 20 steps “Flux1 dev fp8 (20step): GOOD (35s)” Intel Arc B580 12GB, PyTorch 2.8 XPU in Docker (YanWenKun); single 1024x1024 image, pre-warmed inference only (model load excluded) | 35 s / image | — | 2025-08-03 | github.com → |
| reported | Radeon 8060S (Strix Halo) 96 GB | flux1-dev full precision (23.8 GB) + t5xxl_fp16 · 1024x1024 · 20 steps “Steady state | 3.64 s/it | 77.56 s” AMD ROCm blog, Ryzen AI Max+ 395 / Radeon 8060S, 128 GB unified, Windows ComfyUI; first run 103.89 s; vendor-published measurement | 77.56 s / image · 3.64 s/it | — | 2026-07-14 | rocm.blogs.amd.com → |
| reported | RTX 3090 24 GB | fp8 (ComfyUI template) “Nvidia 3090: 26s” ComfyUI 'GPU Benchmark Flux DEV fp8' thread: stock Flux dev fp8 workflow template, time of 2nd/3rd run (no loading); resolution/steps not stated in thread | 26 s / image | — | 2025-07-22 | github.com → |
| reported | RTX 4060 Ti 16 GB | FP8 “Flux-Dev(FP8) … 2回目は72秒から51秒とあまり効果が感じられませんでした。” ComfyUI; same PC before/after swapping RTX 4060 Ti 8GB -> 16GB; 2nd-run times; resolution/steps not stated; 51 s = 16GB card | 51 s / image | — | 2025-01-03 | note.com → |
| reported | RTX 4060 Ti 8 GB | FP8 “Flux-Dev(FP8) … 2回目は72秒から51秒とあまり効果が感じられませんでした。” ComfyUI; same PC before/after swapping RTX 4060 Ti 8GB -> 16GB; 2nd-run times; resolution/steps not stated; 72 s = 8GB card | 72 s / image | — | 2025-01-03 | note.com → |
| reported | RTX 4070 Super 12 GB | Q4_0 GGUF “1.9s/it with Q4_0” RTX 4070 Super 12GB; same post: 2.6s/it with Q5_1, 1.3s/it with NF4; resolution not stated; early (Aug 2024) ComfyUI-GGUF | 1.9 s/it | — | 2024-08-17 | huggingface.co → |
| reported | RTX 4080 16 GB | fp8_e4m3fn weight_dtype · 1024x1024 · 20 steps “weight_dtype (fp8_e4m3fn) with --fast (13sec)” ComfyUI 'RTX 4090 benchmarks - FLUX model' thread; OP settings 1024x1024, 20 steps; Aug 2024 ComfyUI/PyTorch 2.5 dev; with --fast flag (same poster: 19sec without --fast, 28sec def | 13 s / image | — | 2024-08-23 | github.com → |
| reported | RTX 4090 24 GB | fp8 (ComfyUI template) “Prompt executed in 11.28 seconds” ComfyUI 'GPU Benchmark Flux DEV fp8' thread: stock Flux dev fp8 workflow template, time of 2nd/3rd run (no loading); resolution/steps not stated in thread | 11.28 s / image | — | 2025-12-28 | github.com → |
| reported | RTX 4090 24 GB | Q8_0 GGUF · 1024x1024 · 20 steps “15 seconds at the fastest to 17 seconds at the slowest on my RTX 4090 with Euler 20 Steps for 1024x1024 images” stated range 15-17 s; city96 ComfyUI-GGUF Q8 | 15 s / image | — | 2024-08-25 | github.com → |
| reported | RTX 4090 24 GB | fp8 (--fast) · 1024x1024 · 20 steps “Prompt executed in 10.01 seconds” ComfyUI 'RTX 4090 benchmarks - FLUX model' thread; OP settings 1024x1024, 20 steps; Aug 2024 ComfyUI/PyTorch 2.5 dev; FP8 with --fast, GPU at 2.52 GHz/875mV undervolt (9.07 s at 2. | 10.01 s / image | — | 2024-08-26 | github.com → |
| reported | RTX 5060 Ti 16 GB | fp8 (ComfyUI template) “Prompt executed in 25.71 seconds” ComfyUI 'GPU Benchmark Flux DEV fp8' thread: stock Flux dev fp8 workflow template, time of 2nd/3rd run (no loading); resolution/steps not stated in thread; poster's log shows 16311 | 25.71 s / image | — | 2025-08-04 | github.com → |
| reported | RTX 5090 32 GB | fp8 (ComfyUI template) “Getting 8.78s at 2.38it/s for 3 runs.” ComfyUI 'GPU Benchmark Flux DEV fp8' thread: stock Flux dev fp8 workflow template, time of 2nd/3rd run (no loading); resolution/steps not stated in thread; Inno3D RTX 5090 X3 OC | 8.78 s / image · 2.38 it/s | — | 2025-08-05 | github.com → |
Other people's numbers are copied as published, with a link. Send yours.
09Training a LoRA for FLUX.1 dev
| Trainer | VRAM | Type | Settings and quote | Source |
|---|---|---|---|---|
| sd-scripts | 8 GB | stated minimum | --fp8_base, --blocks_to_swap 28, fp8 T5XXL recommended; table also: 24GB batch 2, 16GB batch 1 + swap, 12GB swap 16 + AdamW8bit, 10GB swap 22 “8GB VRAM: Use --blocks_to_swap 28, recommend fp8 format for T5XXL” | github.com → |
| SimpleTuner | 10 GB | stated minimum | Rank-16 LoRA; NF4 base ~9 GB (int8 ~18 GB, int4 ~13 GB, unquantised ~30 GB); lowest config 512px, batch 1, Lion8bit paged; 1024px needs >=12 GB. Guide example uses FLUX.1 Krea “the absolute minimum is a single 3080 10G” | github.com → |
| fluxgym | 12 GB | stated minimum | 12G preset: kohya sd-scripts backend, --fp8_base, Adafactor, --split_mode, train_blocks=single, gradient checkpointing, cached TE outputs; default 512px, rank 4 “Dead simple web UI for training FLUX LoRA with LOW VRAM (12GB/16GB/20GB) support.” | github.com → |
| OneTrainer | 12 GB | stated minimum | Wiki Flux page; no specific settings given (NF4/fp8 mentioned nearby); 8GB possible with GGUF “It is possible to train a Flux Lora on a GPU with 12GB of VRAM.” | github.com → |
| ai-toolkit | 24 GB | stated minimum | Historical README requirement (removed from README on 2026-03-31 in commit ad474e3); 8-bit quantized base, low_vram flag if GPU drives monitors “You currently need a GPU with at least 24GB of VRAM to train FLUX.1.” | github.com → |
| ai-toolkit | 24 GB | example run | Current official example config: rank 16, batch 1, 512/768/1024 buckets, gradient checkpointing, quantize: true (8-bit); README still points to this file “Copy the example config file located at config/examples/train_lora_flux_24gb.yaml” | github.com → |
reported From each trainer's own docs, 2026-09-25. Why the figures differ →
10Every file tracked for FLUX.1 dev
| File | Type | Size | Repo |
|---|---|---|---|
| flux1-dev-fp8-e4m3fn.safetensors | FP8 | 11.90 GB | Kijai/flux-fp8 → |
| flux1-dev-fp8-e5m2.safetensors | FP8 | 11.90 GB | Kijai/flux-fp8 → |
| flux1-dev.safetensors | BF16 | 23.80 GB | black-forest-labs/FLUX.1-dev → |
| flux1-dev-F16.gguf | F16 | 23.80 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q8_0.gguf | Q8_0 | 12.71 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q6_K.gguf | Q6_K | 9.86 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q5_1.gguf | Q5_1 | 9.01 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q5_K_S.gguf | Q5_K_S | 8.29 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q5_0.gguf | Q5_0 | 8.27 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q4_1.gguf | Q4_1 | 7.53 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q4_K_S.gguf | Q4_K_S | 6.81 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q4_0.gguf | Q4_0 | 6.79 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q3_K_S.gguf | Q3_K_S | 5.23 GB | city96/FLUX.1-dev-gguf → |
| flux1-dev-Q2_K.gguf | Q2_K | 4.03 GB | city96/FLUX.1-dev-gguf → |
Text encoders: clip_l + T5-XXL. VAE ae.safetensors 335304388 bytes (BFL repo).