Skip to main content
株式会社オブライト

Articles tagged "マルチモーダル"

11 articles

AI2026-11-05
LongCat-2.5 Explained: Meituan's 1.6T Agent Model and API
LongCat-2.5 is Meituan's 1.6T MoE multimodal agent model (48B active). Weights unreleased, API only. Covers endpoints, Claude Code setup, pricing, caveats.
LongCat-2.5MoEAPI料金
AI2026-10-24
MiniMax M3.1 Flash Requirements: 428B MoE at ~250GB, 512GB Mac or 4 GPUs [2026]
MiniMax M3.1 Flash (428B MoE, ~23B active): ~250GB weights at 4-bit, 260-300GB RAM. Needs a 512GB Mac or 4 GPUs. Sizes, KV cache, API cost. Updated Oct 2026
RequirementsVRAMローカルLLM
AI2026-10-20
Nemotron 3.5 Bolt Requirements: 74B in 22GB, RTX 5090 & 32GB Mac [2026]
Nemotron 3.5 Bolt 74B-A9B (24GB): ~22GB GGUF, 24-32GB memory; RTX 5090 or 32GB Mac minimum. Context 128K/256K, tok/s, vs Gemma 4, setup. Updated Oct 2026.
RequirementsVRAMローカルLLM
AI2026-10-19
MiniCPM-V 4.7 Requirements: 35B-A3B VRAM & GPU [2026]
MiniCPM-V 4.7 35B-A3B (Apache-2.0) needs ~20-22GB at 4-bit, 70GB+ in BF16 (est.): RTX 4090/5090 or 32GB Mac. iPhone LES, vLLM/GGUF setup. Updated Oct 2026.
RequirementsVRAMローカルLLM
AI2026-10-12
EmbeddingGemma 2 Requirements: RAM from 191MB, No GPU Needed [Memory Table, Setup & RAG, 2026]
EmbeddingGemma 2 runs in 191MB RAM (text only) and about 1.5GB BF16 for all modalities, no GPU. Memory table, setup, local RAG. October 2026.
RequirementsGoogle DeepMindRAG
AI2026-09-19
Qwen3.8-Omni-Flash: 1M Context, Pricing & Closed Weights
Qwen3.8-Omni-Flash: Alibaba's omni-modal model, 1M-token context, $0.15/million input. Weights closed, no local run; text-only output, unlike its predecessor.
QwenAIマルチモーダル
AI2026-08-22
DeepSeek-V4-Flash-Vision-Exp: A First Look at the New Multimodal API
DeepSeek's V4-Flash-Vision-Exp launched Aug 21, 2026 at V4-Flash pricing. On Aug 31, DeepSeek open-sourced the ~168GB FP4/FP8 weights on Hugging Face under MIT. Update covers local hardware needs and when the API still wins.
DeepSeek V4MoEマルチモーダル
AI2026-08-03
Qwen3.7 Flash Explained: $0.03 per Million Tokens, 1M Context, and What This Closed Vision-Language Model Can (and Can't) Do (2026)
Qwen3.7 Flash: Alibaba's closed vision model, priced from $0.03 per million input tokens, 1M-token context. Tiered pricing, use cases, limits. Updated Aug. 2026.
Qwen 3.7AlibabaAPI料金
AI2026-04-17
Claude Opus 4.7 Complete Guide — SWE-bench 87.6%, Vision 98.5% & New xhigh Effort Mode [April 16, 2026 Release]
Released April 16, 2026, Claude Opus 4.7 achieves SWE-bench Verified 87.6%, Vision accuracy 98.5%, and introduces the new xhigh Effort Control — all at the same price as Opus 4.6. This guide covers every major upgrade to Anthropic's latest flagship model.
Claude Opus 4.7AnthropicSWE-bench
AI2026-04-10
Mistral Small 4 Complete Guide — Unified Reasoning, Multimodal & Code in 119B MoE [2026]
Mistral Small 4, released March 2026, unifies reasoning, multimodal vision, and agentic coding in a 119B MoE model under Apache 2.0. Supports 11 languages including Japanese. Full specs, setup guide, and model comparisons.
Mistral Small 4MoEマルチモーダル
AI2026-03-04
Qwen3.5-9B Multimodal Guide: Running Free Image & Video AI In-House
Learn how to leverage Qwen3.5-9B's early-fusion multimodal architecture for free in-house image and video AI. Covers OCR, product inspection, surveillance analysis, meeting summarization, cloud API comparison, and step-by-step setup for local multimodal inference.
Qwen3.5マルチモーダル画像認識