AI NEWS.ccAI is happening. The future is updating.
♡ Saved tools 0
AI NEWS · Model intelligenceExplore capabilities. Make informed choices. ↗Profiles indexed first · Details continuously enriched
THE AI MODEL DIRECTORY Start exploring models here

Find your ideal AI model.

From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.

Popular searches
84,854 model profiles13108 providers / publishers45 capability categories465 with comparable prices · 30 benchmarked
TText generation▧Image generation▷Video generation⌘Code generation◖Speech synthesis♫Music generation⬡3D modeling▤Document analysis
DISCOVER & COMPARE

Explore AI models 30

Discover models worth your attention

flint-cmf

infosave

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Text generation
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

This repository contains all three dense reasoning models from IBM's Granite 4.2 family: 3B, 8B and 30B, each converted directly from the original bf16 checkpoint to Q4TP and Q8_2F CMF. A CMF is one memory-mapped file containing the weights, tokenizer, exact chat template and integrity hashes. The same artifact runs on CPU, Vulkan (NVIDIA/AMD/Intel), DX12 and Metal; inference needs no Python, PyTorch, CUDA toolkit or model-specific GPU build. Use `--no-think` for a direct answer. Without it, the embedded Granite template opens the model's native ` ... ` reasoning block. Numbers are single-stream `cortiq bench --tokens 100 --core --ignore-eos` steady decode on an NVIDIA A40. They exclude model load and prompt prefill. The 3B Q4TP run prefills at 80.3 tok/s and reaches first token in 0.58 s; its Q8_2F control prefills at 47.5 tok/s and reaches first token in 0.93 s. The 30B Q8_2F file is larger than the A40's safe physical graph live set: Cortiq automatically kept 55 of 64 layers on Vulkan and ran the nine-layer tail on the host. That 100-token run peaked at 43,036 MiB of the A40's 46,068 MiB and completed without steady-state weight uploads.

Text generation
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Text generation
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

Hy-MT2-cmf

infosave

Tencent's Hy-MT2 translation family — 33 languages, instruction-following translation (terminology, style, placeholders, structured data) — as CMF files for `cortiq`: one memory-mapped file per model with the weights, the vendor tokenizer, the exact chat template and per-tensor hashes. The same file runs on the CPU, on Vulkan (NVIDIA / AMD / Intel), DX12 and Apple Metal; no Python, no PyTorch, no CUDA toolkit. **Requires cortiq 0.7.0 or newer.** Earlier runtimes do not know the `hunyuan_v1_dense` / `hy_v3` architectures (and 0.6.9 crashes on any 4-bit embedding — fixed in the same release). ¹ Twelve 512-token windows of wikitext-2 test, exact attention, the same yardstick every card on this account uses. The bf16-class reference for the 1.8B (`q8_2f`, not published) scores 24.77 — the 4-bit file sits within 10% (27.13 vs 24.77) of it. These are translation models: their perplexity on English encyclopedia prose is not what they were trained for, which is why column ² exists.

Translation
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

LFM2.5-cmf

infosave

LiquidAI's LFM2.5 is a hybrid: most layers mix with a short gated convolution and only a few carry full attention, so the state a token needs is small and constant where the convolution runs. These are those checkpoints in the CMF container — a single memory-mapped file read by `cortiq`, a Rust binary with no ML framework under it. GPU via Vulkan/Metal/DX12 with a CPU fallback; NVIDIA, AMD, Intel and Apple silicon read the same file. All three are 4-bit tiled with ladder scales (`q4tp`), quantized straight from the bf16 checkpoints. Steady-state decode, `cortiq bench --core`, single stream, cortiq **0.5.99+** (the whole-token graph learned this family's short-conv mixer and its sigmoid-routed MoE in 0.5.98/0.5.99 — earlier versions decode it an order of magnitude slower).

Text generation
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

> **Model release candidate.** All three weight files are uploaded and SHA-256 verified. > Text and greedy MTP checks pass; strict multimodal acceptance is still incomplete. > **Engine: Cortiq 0.7.7** · crates.io. Older published versions do not include this MiMo integration. **These are two complete file sets, not two copies of the 164-GB backbone.** Full includes the same text weights plus a **1.241-GB multimodal companion**. To upgrade from Text-only, download only the `.mm.cmf` file into the same folder. Text-only does not download or load the media towers. MiMo is a mixture-of-experts model with approximately **310 billion total parameters**, not a 15-billion-parameter checkpoint. Only a subset (roughly 15 billion parameters) is active per token, but **all experts must be stored**. Even a hypothetical uniform four-bit representation of 310 billion parameters would occupy about **155 GB**, before scales, metadata and higher-precision tensors. This conversion intentionally retains q8 and float tensors where needed.

Text generation
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗

Nanbeige/Nanbeige4.2-3B converted to the CMF format: a single mmap-served file executed by a pure-Rust runtime. Nanbeige 4.2 is a **Looped Transformer**: 22 physical layers applied twice (44 virtual layers) with a re-norm at each loop boundary — the engine executes the loop natively — and a reasoning model that thinks before it answers. Measured on a **fanless MacBook Air (Apple M4)** — 10-core CPU (4 performance + 6 efficiency), 10-core GPU, 24 GB unified memory, macOS 27. No external cooling, no overclock, nothing plugged in.

Text generation
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
Source / docs ↗
COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ
How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

AI NEWS · From information to decisions

Follow trends. Find tools. Explore models.

Explore AI news ↗Discover AI tools ↗