Written by Jakub Rusinowski · Last updated June 26, 2026
Reading images, screenshots, charts and diagrams alongside text.
Top pick: Qwen 3.7 35B-A3B
Scores 95.5/100 for vision and image understanding. 35B parameters, needing about 21.9 GB at Q4_K_M, 256K context, Apache-2.0.
| Model | Score | Params | Context | Licence | Quality index |
|---|---|---|---|---|---|
| 1. Qwen 3.7 35B-A3B | 95.5 | 35B | 256K | Apache-2.0 | — (estimated) |
| 2. Gemma 4 31B | 95.2 | 31B | 250K | Apache-2.0 | — (estimated) |
| 3. Qwen 3.5 14B | 95 | 14B | 125K | Apache 2.0 | — (estimated) |
| 4. Qwen 3.6 35B-A3B | 94.8 | 35B | 256K | Apache-2.0 | — (estimated) |
| 5. Gemma 4 27B ⭐ | 94.2 | 27B | 125K | Gemma License (commercial OK) | — (estimated) |
| 6. Kimi K2.6 | 94 | 32B | 125K | Kimi License (research) | — (estimated) |
The strongest model overall is rarely the right answer — what matters is the strongest model that fits the memory you have. These picks are re-ranked per tier, so each one uses its budget rather than simply being small.
| Memory | Typical hardware | Recommended models |
|---|---|---|
| 8 GB | RTX 4060, RTX 3070, base MacBook Air | Gemma 4 E4B (91.6) Llama 3.2 11B Vision Instruct (91.6) Qwen 2.5 VL 7B Instruct (90.7) |
| 12 GB | RTX 3060 12 GB, RTX 5070 | Qwen 3.5 14B (95.7) Gemma 4 12B (92.3) Gemma 4 12B (Unified) (92) |
| 16 GB | RTX 5080, RTX 4080, RX 9070 XT | Qwen 3.5 14B (95.4) Mistral Small 3.1 24B (95.2) Gemma 4 12B (91.2) |
| 24 GB | RTX 4090, RTX 3090, RX 7900 XTX | Qwen 3.7 35B-A3B (98.1) Gemma 4 31B (97.8) Qwen 3.6 35B-A3B (97.4) |
| 48 GB | RTX 6000 Ada, MacBook Pro M4 Max 48 GB | Qwen 3.5 72B (99.7) Qwen 3.7 35B-A3B (96.5) Qwen 3.6 35B-A3B (95.8) |
| 128 GB+ | Mac Studio, DGX Spark, multi-GPU | Qwen 3.5 72B (96.9) Llama 3.2 90B Vision Instruct (95.2) Mistral Small 4 119B-A6.5B (93.1) |
Vision capability is a hard gate — text-only models are excluded outright rather than penalised, so this ranking is drawn from a genuinely different candidate pool than every other workload here.
Worked example — Qwen 3.7 35B-A3B: capability 92.7 × 0.422, quality 92.7 × 0.248, context 100 × 0.161, license 100 × 0.039, accessibility 80 × 0.13 + 3 tag bonus (multimodal).
Requirements applied: context floor 8,192 tokens (ideal 131,072), quality floor 45, licence weight 0.35, latency weight 0.5. Vision capability is required.
Qwen 3.7 35B-A3B, scoring 95.5/100 against this workload's published requirements. 31 models qualified.
A credible answer starts at 8 GB of memory. Larger budgets unlock materially stronger models — the table above lists the best pick at each tier.
Vision capability is a hard gate — text-only models are excluded outright rather than penalised, so this ranking is drawn from a genuinely different candidate pool than every other workload here.