MODEL · MICROSOFT · 3.8B (MMDIT 48-BLOCK + FLUX.2 SEMANTIC VAE + MULTI-LAYER GPT-OSS TEXT FEATURES)
Microsoft Lens (3.8B, MIT) — WITHDRAWN
⚠️ **Withdrawn by Microsoft — you can no longer download this.** As of our August 3, 2026 check, all three Hugging Face repos (`microsoft/Lens`, `-Turbo`, `-Base`) return 401 to anonymous access, `github.com/microsoft/Lens` returns 404, and no repo matching "lens" appears among the 534 repos Microsoft currently lists on the Hub. We are keeping this page up rather than deleting it because we recommended Lens-Turbo as a planner pick from May 22 to August 3, and a reader who acted on that deserves to find out what happened instead of hitting a dead link. What it was: Microsoft's first foundational text-to-image model, a 3.8B MMDiT trunk paired with FLUX.2's semantic VAE and multi-layer features from a frozen GPT-OSS text model, shipped as a three-step ladder (`Lens-Base` 50-step supervised, `Lens` 20-step RL-tuned, `Lens-Turbo` 4-step distilled) under MIT. Note the pattern: it was uploaded and pulled once in mid-May before the May 25 public release, so this is the second withdrawal.
License: MIT · Context: Up to 1,440 × 1,440 native; aspect ratios 1:2 to 2:1 · Released: May 19, 2026 (paper arxiv 2605.21573; HF model card finalized May 18)
The decision in five lines
- The call
- Consider — runnable locally, family reference
- Best for
- Local evaluation and family reference
- Runs on
- 23 hardware picks fit (cheapest: Intel Arc B580 12 GB · $249)
- Watch out
- If you already have the weights locally, the MIT licence you received them under still stands; a withdrawal does not retroactively revoke a licence already granted.
- Evidence
- Estimated
- 3.8B (MMDiT 48-block + FLUX.2 semantic VAE + multi-layer GPT-OSS text features)
- PARAMETERS
- IMAGE GEN
- TYPE
- Up
- CONTEXT
- ~8 GB BF16 on A100/V100 fallback; MXFP4 native on Hopper+ for ~half
- VRAM AT Q4
Where we recommend this
This model isn’t currently in an active planner slot. See the runner notes below if you’re running it anyway.
The call
⚠️ **Withdrawn by Microsoft — you can no longer download this.** As of our August 3, 2026 check, all three Hugging Face repos (`microsoft/Lens`, `-Turbo`, `-Base`) return 401 to anonymous access, `github.com/microsoft/Lens` returns 404, and no repo matching "lens" appears among the 534 repos Microsoft currently lists on the Hub. We are keeping this page up rather than deleting it because we recommended Lens-Turbo as a planner pick from May 22 to August 3, and a reader who acted on that deserves to find out what happened instead of hitting a dead link. What it was: Microsoft's first foundational text-to-image model, a 3.8B MMDiT trunk paired with FLUX.2's semantic VAE and multi-layer features from a frozen GPT-OSS text model, shipped as a three-step ladder (`Lens-Base` 50-step supervised, `Lens` 20-step RL-tuned, `Lens-Turbo` 4-step distilled) under MIT. Note the pattern: it was uploaded and pulled once in mid-May before the May 25 public release, so this is the second withdrawal.
When not to use: Any new work — it is not obtainable. If you already have the weights locally, the MIT licence you received them under still stands; a withdrawal does not retroactively revoke a licence already granted. For a current pick at this tier use **Z-Image-Turbo** (6B, Apache 2.0, 8-step, community-proven), which replaced Lens in our image.high band, or **HiDream-O1-Image** (8B, MIT) for the quality ceiling.
Runner notes
Nothing to run — the repos are gone. Kept here as a dated record. The wider lesson is the one this site keeps relearning: a permissive licence is worth very little if the weights stop being downloadable, and "open source" is a property of an artifact you actually hold, not of an announcement. This is the second time in 2026 a model we tracked became unavailable after we recommended it — Claude Fable 5 was switched off for 19 days in June under an export-control directive. Prefer picks with wide community mirroring; a model that exists in a dozen community quant repos is far harder to withdraw than one that lives only in a vendor org.
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.
- Intel Arc B580 12 GBGood · 1.3× 12 GB · $249–$299
- NVIDIA RTX 3060 12 GBGood · 1.3× 12 GB · $280–$400
- Minisforum UM890 ProPerfect · 2.6× 32 GB DDR5 (shared) · $463–$580 all-in
- RTX 5060 Ti 16 GBPerfect · 1.7× 16 GB · $560–$610
- AMD Radeon RX 9070 XTPerfect · 1.7× 16 GB · $649–$779
- Mac Mini M4 16 GBGood · 1.2× 16 GB unified · $799 (new floor) / $499–$599 (eBay/residuals)
- AMD Radeon RX 7900 XTXPerfect · 2.6× 24 GB · $810 used / ~$1,340 new
- NVIDIA RTX 3090 (used, single)Perfect · 2.6× 24 GB · $950–$1,200
- NVIDIA RTX 5070 TiPerfect · 1.7× 16 GB · $980–$1,300
- NVIDIA RTX 5080Perfect · 1.7× 16 GB · $1,250–$1,400
- MacBook Air M5 24 GBPerfect · 1.7× 24 GB unified · $1,499–$1,899
- Mac Mini M4 Pro 24 GBPerfect · 1.7× 24 GB unified · $1,599
- Dual RTX 3090 (used)Perfect · 5.2× 48 GB · $1,800–$2,500 all-in
- NVIDIA RTX 4090Perfect · 2.6× 24 GB · $2,200–$2,800
- M5 Pro MacBook Pro 48 GBPerfect · 3.5× 48 GB unified · $2,999–$3,599
- Framework Desktop (Ryzen AI Max+ 395)Perfect · 9.2× 128 GB unified · $3,449 (128 GB config)
- NVIDIA RTX 5090Perfect · 3.4× 32 GB · $3,500–$4,300
- NVIDIA RTX A6000 (48 GB, used)Perfect · 5.2× 48 GB ECC · $3,500–$4,500
- Mac Studio M4 Max 64 GBPerfect · 4.6× 64 GB unified · $3,799
- NVIDIA DGX SparkPerfect · 9.2× 128 GB unified · $4,699
- M5 Max MacBook Pro 64 GBPerfect · 4.6× 64 GB unified · ~$5,199 (est.; June 25 2026 increase)
- Mac Studio M3 Ultra 96 GBPerfect · 6.9× 96 GB unified · $5,299
- Dual RTX 5090Perfect · 6.9× 64 GB (2×32) · $8,500–$10,500
Next step
Find-by-model — see what hardware runs this→