Chroma1-HD VRAM requirements
An 8.9B community model built from FLUX.1 schnell, Apache-2.0 licensed, with a big fine-tuning scene.
TypeImage
Parameters8.9B
Fits entirely from6 GB
8-bit or better from12 GB
01Measured on my RTX 5060 Ti 16 GB
FP8 · 1024×1024
54.4s / image
Chroma1-HD-fp8mixed.safetensors
Peak VRAM15.4 GB
Run range54.1–54.8 s
02The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 17.8 GB | 20.1 GB | 21 GB | the original weights | lodestones/Chroma1-HD → |
| Q8_0 | 9.7 GB | 12.0 GB | 13 GB | practically identical to the original | silveroxides/Chroma1-HD-GGUF → |
| FP8 | 9.2 GB | 11.5 GB | 12 GB | practically identical to the original | Comfy-Org/Chroma1-HD_repackaged → |
| Q6_K | 7.7 GB | 10.0 GB | 10 GB | very close to the original | silveroxides/Chroma1-HD-GGUF → |
| Q5_K_M | 6.7 GB | 9.0 GB | 9 GB | close; small differences in fine detail | silveroxides/Chroma1-HD-GGUF → |
| Q4_K_M | 5.6 GB | 7.9 GB | 8 GB | good; some loss in fine detail and text | silveroxides/Chroma1-HD-GGUF → |
| Q3_K_S | 4.3 GB | 6.6 GB | 7 GB | noticeable loss of detail | silveroxides/Chroma1-HD-GGUF → |
| Q2_K | 3.4 GB | 5.7 GB | 6 GB | heavy loss; a last resort | silveroxides/Chroma1-HD-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). Drag the file into ComfyUI. All workflows →
03By amount of VRAM
04Best GPU for Chroma1-HD
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for Chroma1-HD → 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 | Tight | Q2_K | 5.7 GB |
| RTX 3050 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 2070 Super 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 2080 Super 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 3050 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 3060 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 3060 Ti 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 3070 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 3070 Ti 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 4060 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 4060 Ti 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 5050 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 5060 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 5060 Ti 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RX 7600 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RX 9050 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RX 9060 XT 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| Arc B570 10 GB | 10 GB | Runs | Q6_K | 10.0 GB |
| RTX 3080 10 GB | 10 GB | Runs | Q6_K | 10.0 GB |
| RTX 2080 Ti 11 GB | 11 GB | Runs | Q6_K | 10.0 GB |
| Arc B580 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 2060 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 3060 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 3080 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 3080 Ti 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 4070 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 4070 Super 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 4070 Ti 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 5070 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RX 7700 XT 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RX 9070 GRE 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| Arc A770 16 GB | 16 GB | Runs well | Q8_0 | 12.0 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RTX 4080 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RTX 5080 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RX 7600 XT 16 GB | 16 GB | Runs well | Q8_0 | 12.0 GB |
| RX 7800 XT 16 GB | 16 GB | Runs well | Q8_0 | 12.0 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs well | Q8_0 | 12.0 GB |
| RX 9060 XT 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RX 9070 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RX 9070 XT 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | Q8_0 | 12.0 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | 16-bit | 20.1 GB |
| RTX 3090 24 GB | 24 GB | Runs well | 16-bit | 20.1 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | 16-bit | 20.1 GB |
| RTX 4090 24 GB | 24 GB | Runs well | 16-bit | 20.1 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | 16-bit | 20.1 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | 16-bit | 20.1 GB |
| RTX 5090 32 GB | 32 GB | Runs well | 16-bit | 20.1 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Offload only | Q2_K | 5.7 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Offload only | Q2_K | 5.7 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Tight | Q2_K | 5.7 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RX 7600M 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RX 7600M XT 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RX 7600S 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RX 7700S 8 GB | 8 GB | Runs | Q4_K_M | 7.9 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RX 7800M 12 GB | 12 GB | Runs well | FP8 | 11.5 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs well | Q8_0 | 12.0 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs well | Q8_0 | 12.0 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs well | FP8 | 11.5 GB |
| RX 7900M 16 GB | 16 GB | Runs well | Q8_0 | 12.0 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | 16-bit | 20.1 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 20.1 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 20.1 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Runs well | Q8_0 | 12.0 GB |
| Mac 18 GB | 14.4 GB | Runs well | Q8_0 | 12.0 GB |
| Mac 24 GB | 19.6 GB | Runs well | Q8_0 | 12.0 GB |
| Mac 32 GB | 26.8 GB | Runs well | 16-bit | 20.1 GB |
| Mac 36 GB | 30.2 GB | Runs well | 16-bit | 20.1 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 20.1 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 20.1 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 20.1 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 20.1 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 20.1 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 20.1 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 20.1 GB |
06Text encoder, VAE and other files
| File | Folder | Size | When | |
|---|---|---|---|---|
| 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 | Chroma1-HD-fp8mixed.safetensors · 1024x1024 · 26 steps 26 steps, CFG 4 with a negative prompt, euler/beta. Text encoder T5-XXL FP8, FLUX VAE (ae). 3 timed runs after 1 warm-up (59.0 s incl. loading). ComfyUI 0.38.1 portable, PyTorch 2. | 54.37 s / image | 15.4 GB | 2026-10-12 |
09Training a LoRA for Chroma1-HD
| Trainer | VRAM | Type | Settings and quote | Source |
|---|---|---|---|---|
| SimpleTuner | 8 GB | stated minimum | Rank-16 LoRA, NF4 base (int4 ~11 GB, int8 ~16 GB, unquantised ~28 GB); realistic GPU minimum RTX 3090/4090 class “~8 GB VRAM with NF4 + bf16” | github.com → |
| OneTrainer | 8 GB | example run | Official preset for lodestones/Chroma1-HD: 512px, batch 2, transformer fp8, TE fp8, layer offload fraction 0.6 “See presets for VRAM settings, with 8GB, 16GB and 24GB presets being created for both Finetune and Lora” | github.com → |
| ai-toolkit | 24 GB | example run | Official example config (points to lodestones/Chroma, not HD): rank 16, batch 1, 512/768/1024, gradient checkpointing, 8-bit quantized base “train_lora_chroma_24gb.yaml” | github.com → |
reported From each trainer's own docs, 2026-09-25. Why the figures differ →
10Every file tracked for Chroma1-HD
| File | Type | Size | Repo |
|---|---|---|---|
| Chroma1-HD-fp8mixed.safetensors | FP8 | 9.19 GB | Comfy-Org/Chroma1-HD_repackaged → |
| Chroma1-HD.safetensors | 16-bit | 17.80 GB | lodestones/Chroma1-HD → |
| Chroma1-HD-BF16.gguf | BF16 | 17.80 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q8_0.gguf | Q8_0 | 9.74 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q6_K.gguf | Q6_K | 7.65 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q5_1.gguf | Q5_1 | 7.05 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q5_K_M.gguf | Q5_K_M | 6.65 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q5_0.gguf | Q5_0 | 6.51 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q5_K_S.gguf | Q5_K_S | 6.51 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q4_1.gguf | Q4_1 | 5.97 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q4_K_M.gguf | Q4_K_M | 5.57 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q4_0.gguf | Q4_0 | 5.43 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q4_K_S.gguf | Q4_K_S | 5.43 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q3_K_S.gguf | Q3_K_S | 4.29 GB | silveroxides/Chroma1-HD-GGUF → |
| Chroma1-HD-Q2_K.gguf | Q2_K | 3.41 GB | silveroxides/Chroma1-HD-GGUF → |
FLUX.1-schnell derivative pruned to 8.9B by lodestones. Uses T5-XXL only (no clip_l).