Post
661
Can a text-only model + a vision toolkit (mm-ctx) match a native vision model?
We benchmarked 4 setups on 23 multimodal tasks (image, video, audio, PDF):
• glm-5.2 (text-only) + mm-ctx: 88.4
• gemini-3.5-flash (vision): 83
• deepseek-v4-pro (text-only) + mm-ctx: 79.4
• qwen3.6-35b-a3b (vision): 44.3
The best text-only setup
• 1.5x faster (100s vs 150s mean per task)
• the only setup with zero timeouts (46/46 completed; gemini timed out 4x on bulk-image and long-video tasks)
• the only setup stable across runs (88.5 / 88.4)
• top on video (100.0), image (91.7), and PDF (90.0) tasks
The trade-offs: the toolkit consumed 3.3x more tokens (4.25M vs 1.28M), and lost on audio (85.6 vs 71.3).
On completed tasks alone the two are nearly identical (91.0 vs 88.4): the toolkit's edge is efficient extraction that keeps long media tasks inside the time budget.
Full report: https://huggingface.co/blog/vlm-run/text-only-models-with-mm
We benchmarked 4 setups on 23 multimodal tasks (image, video, audio, PDF):
• glm-5.2 (text-only) + mm-ctx: 88.4
• gemini-3.5-flash (vision): 83
• deepseek-v4-pro (text-only) + mm-ctx: 79.4
• qwen3.6-35b-a3b (vision): 44.3
The best text-only setup
glm-5.2 + mm outperformed gemini-3.5-flash, the top vision model, by 5.4 points (6.5%). It was also:• 1.5x faster (100s vs 150s mean per task)
• the only setup with zero timeouts (46/46 completed; gemini timed out 4x on bulk-image and long-video tasks)
• the only setup stable across runs (88.5 / 88.4)
• top on video (100.0), image (91.7), and PDF (90.0) tasks
The trade-offs: the toolkit consumed 3.3x more tokens (4.25M vs 1.28M), and lost on audio (85.6 vs 71.3).
On completed tasks alone the two are nearly identical (91.0 vs 88.4): the toolkit's edge is efficient extraction that keeps long media tasks inside the time budget.
Full report: https://huggingface.co/blog/vlm-run/text-only-models-with-mm
