MODEL · HIDREAM · 17B (SAME ACROSS ALL THREE; DEV AND FAST ARE STEP-DISTILLED, NOT PRUNED)
HiDream-I1 (Full / Dev / Fast)
17B MMDiT open-weights image foundation, MIT-licensed, SOTA-at-release. Full/Dev/Fast ladder distilled down the step count. The MIT license is a big unlock for production commercial pipelines vs FLUX dev.
License: MIT (clean commercial — rare for 17B image model) · Context: Full ~50 steps / Dev ~28 / Fast ~16 · Released: April 7, 2025
The decision in five lines
- The call
- Skip for local — for image
- Best for
- image
- Runs on
- 16 hardware picks fit (cheapest: Minisforum UM890 Pro · $463 barebone (no RAM / SSD); $991 with 32 GB / 1 TB — Minisforum US store, Sep 15 2026)
- Watch out
- At 12 GB VRAM — even Fast FP8 reports 16–18 GB.
- Evidence
- Estimated
- 17B (same across all three; Dev and Fast are step-distilled, not pruned)
- PARAMETERS
- IMAGE GEN
- TYPE
- Full
- CONTEXT
- ~16–18 GB (FP8) / ~20–27 GB (BF16 Full)
- VRAM AT Q4
Where we recommend this
Every tier slot in the planner where this model is a top or alternate pick. Pulled live from planner.js — when the planner refreshes, this table stays current.
The call
17B MMDiT open-weights image foundation, MIT-licensed, SOTA-at-release. Full/Dev/Fast ladder distilled down the step count. The MIT license is a big unlock for production commercial pipelines vs FLUX dev.
When not to use: At 12 GB VRAM — even Fast FP8 reports 16–18 GB. For those budgets, FLUX.2 klein 4B or Z-Image-Turbo are the sane picks. FLUX.2 [dev] still edges it on complex compositions.
Runner notes
ComfyUI. FP8 variants land at ~16–18 GB VRAM; BF16 full wants 20–27 GB. Fast is 1.5–2× quicker than Full at a small quality cost.
Hardware that fits
Every hardware pick whose memory fits this model at the quant we recommend. Sorted cheapest-first — the top row is your best-value fit. Click through for the full buyer’s guide.
- Minisforum UM890 ProGood · 1.4× 32 GB DDR5 (shared) · $463 barebone (no RAM / SSD); $991 with 32 GB / 1 TB — Minisforum US store, Sep 15 2026
- NVIDIA RTX 3090 (used, single)Good · 1.4× 24 GB · $950–$1,200
- AMD Radeon RX 7900 XTXGood · 1.4× 24 GB · $1,300–$1,500 new (no refurb in stock Sep 15 2026)
- MacBook Air M5 24 GBRequires tweak · 1.2× 24 GB unified · $1,499–$1,899
- Mac Mini M4 Pro 24 GBRequires tweak · 1.2× 24 GB unified · $1,699 (M5 Pro successor, 24 GB / 512 GB, pre-order; M4 Pro discontinued Aug 25 2026)
- Dual RTX 3090 (used)Perfect · 2.7× 48 GB · $1,800–$2,500 all-in
- NVIDIA RTX 4090Good · 1.4× 24 GB · $2,200–$2,800
- M5 Pro MacBook Pro 48 GBPerfect · 1.8× 48 GB unified · $2,999–$3,599
- Framework Desktop (Ryzen AI Max+ 395)Perfect · 4.9× 128 GB unified · $3,449 (128 GB config)
- NVIDIA RTX A6000 (48 GB, used)Perfect · 2.7× 48 GB ECC · $3,500–$4,500
- Mac Studio M4 Max 64 GBPerfect · 2.4× 64 GB unified · $3,799 (M5 Max successor, 64 GB / 1 TB, pre-order; M4 Max discontinued Aug 25 2026)
- NVIDIA DGX SparkPerfect · 4.9× 128 GB unified · $4,699
- M5 Max MacBook Pro 64 GBPerfect · 2.4× 64 GB unified · ~$5,199 (est.; June 25 2026 increase)
- Mac Studio M3 Ultra 96 GBPerfect · 3.7× 96 GB unified · $5,499 (M5 Ultra successor, 96 GB / 1 TB, pre-order; M3 Ultra discontinued Aug 25 2026)
- NVIDIA RTX 5090Perfect · 1.8× 32 GB · $6,450–$7,000 (new, in stock)
- Dual RTX 5090Perfect · 3.6× 64 GB (2×32) · $13,300–$14,000 all-in (two cards alone are ~$12,900 at the Sep 15 2026 Newegg floor)
Next step
Find-by-model — see what hardware runs this→