AI NEWS · 模型情报站发现能力边界,让每一次选择更有依据 ↗基础档案先收录 · 缺失资料持续补齐
THE AI MODEL DIRECTORY 模型探索,从这里开始

找到适合你的 AI 模型。

从语言到影像,从开源到 API。读懂模型能力、比较真实成本,
为你的下一个想法,找到合适的智能引擎。

热门探索
85,021 款模型档案13202 家厂商 / 发布者45 个能力分类465 款有可比报价 · 30 款有公开评测
T文本生成▧图像生成▷视频生成⌘代码生成◖语音合成♫音乐生成⬡3D 建模▤文档分析
DISCOVER & COMPARE

探索 AI 模型 62

为你发现值得关注的模型

**Abliterated · No guardrails · PTQ1_0 dense-ternary 1.75 bpw · 5.9 GB · Runs on a laptop / single GPU · Vision-capable** > ⚠️ **Re-download notice (2026-09-17 20:44 PDT / 2026-09-18 03:44 UTC)** — an earlier build of this model had a coherence bug in reasoning modes (`low`/`xhigh`) that could cause token loops on some prompts. This version fixes it. If you downloaded before this timestamp, please pull the latest .gguf. Bonsai 2 27B — PrismML's ternary compression of Qwen3.8-27B — with the refusal circuitry surgically removed at the weight level while capability, vision, reasoning modes (`off`/`low`/`xhigh`), tool use, and multi-turn coherence are preserved. Full 27B-class hybrid Attention + SSM (GatedDeltaNet) architecture in a **5.9 GB** 1bit GGUF.

译文排队中 · 当前显示来源原文

输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

**Abliterated · No guardrails · PQ2_0 ternary 2.13 bpw · 7.2 GB · Runs on a laptop / single GPU · Vision-capable** > ⚠️ **Re-download notice (2026-09-17 20:44 PDT / 2026-09-18 03:44 UTC)** — an earlier build of this model had a coherence bug in reasoning modes (`low`/`xhigh`) that could cause token loops on some prompts. This version fixes it. If you downloaded before this timestamp, please pull the latest .gguf. **Proprietary weight-level abliteration** by the dealignai research team. Byte-identical to the base ternary quant everywhere except a small set of tensors that carry the refusal circuit. Drop-in replacement for the ternary base at inference — same tokenizer, same chat template, same reasoning modes, same vision projector interface.

译文排队中 · 当前显示来源原文

输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

Native **Q1_0** GGUF release of the Bonsai 27B CRACK model for the Prism llama.cpp fork. This repo contains the quantized language model and the matching F16 Qwen3VL multimodal projector. The projector contains 334 tensors and both temporal patch slices `v.patch_embd.weight` and `v.patch_embd.weight.1` (`temporal_patch_size=2`). The original image and video processor configuration files are included. Image input is live-tested. Direct video-container input depends on the Prism runtime surface; extract frames or use a compatible Qwen3VL video client when the CLI does not accept the container directly. See `preprocessor_config.json` and `video_preprocessor_config.json` for the retained preprocessing metadata. MMLU is the same fixed, stratified 200-question sample for all rows. It uses next-token A/B/C/D logits with reasoning/thinking disabled; it is not a claim for the complete official MMLU suite. HB is the complete unsliced 320-case text run. The live text smoke measured 58.51–58.66 tok/s and the image request measured 58.53 tok/s on an Apple M5 Max using the Prism Metal runtime.

译文排队中 · 当前显示来源原文

输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

> [!NOTE] > **Please credit if you build on this.** If you redistribute, quantize, fine-tune, serve, benchmark, or write about this model, a line like > _"Based on `dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8`"_ > in your model card or write-up means a lot. Thank you. > [!TIP] > **Quantizing this FP8 checkpoint directly won't give the best quality.** Low-bit quants that are naively derived from these weights carry quantization error on top of the abliteration edit, and compliance can regress at low bits. For a proper low-bit release, redo the abliteration pipeline on the target precision rather than quantizing this bundle after the fact. (The sibling EXL3 2.9 bpw UNCENSORED is built that way end-to-end.) > [!IMPORTANT] > Native FP8 (e4m3) with ue8m0 block scales + FP4 MoE experts. 1M-token context. Multimodal > (image + video) + tool calling + reasoning-effort tiers (`low` / `high` / `max`) all preserved. > **Recommended sampling:** `temperature=1.0`, `top_p=1.0`, `max_tokens ≥ 256K` (heavy reasoner).

译文排队中 · 当前显示来源原文

输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

**Abliterated · No guardrails · Native FP8 · 1M-token context · Vision + tools · Reasoning-max default** **Proprietary weight-level abliteration** developed by the dealignai research team. No custom `model.py`, no runtime hooks, no steering vectors — it's a standard checkpoint that loads exactly like the base model. The refusal circuitry is surgically removed while every capability-critical component (routed experts, Engram memory, CSA2 sparse attention, DSpark draft head, vision tower, router gates, norms, embeddings) is preserved byte-identical to the base. Every response 4-tier graded (HARD_REF / SOFT_RED / HEDGE / COMPLY), with reasoning-trace verification at effort=max.

译文排队中 · 当前显示来源原文

输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

**Abliterated Gemma 4 31B Dense — 60 layers, hybrid sliding/global attention, multimodal VL** > **Recommended: Run in vMLX** for best experience including thinking mode support, repetition penalty, and vision capabilities. - **Improved abliteration**: Higher quality refusal vector extraction - **Thinking-ON stability**: Clean thinking cycle — no more degenerate loops - **Same compliance**: 93.7% HarmBench - **Architecture-aware**: Tuned for Gemma 4's hybrid attention design

译文排队中 · 当前显示来源原文

输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

a **CRACK** release by dealignai · Twitter @dealignai > [!IMPORTANT] > **Runtime notes** — field-tested on 8× DGX Spark GB10 by @0xMagnus (discussion): > > - **`reasoning_effort` only honors `"low"` and `"high"`.** Every other value — `off`, `medium`, `max`, unset, or an unquoted YAML `off:` (parses as boolean `false`) — falls through to `max`. There is no way to disable reasoning on this checkpoint; pass `"low"` for minimum. > - **On FP8, prefer `low` for agent / tool-loop use.** At `high`/`max` the model can spend the whole `max_tokens` budget inside ` ` and return zero answer tokens (finish=`length`); sampling params (temp 0 + rep 1.05, temp 0.7 / top-p 0.95) do not rescue it. It is budget exhaustion, not a loop. If you must run `high`/`max`, give `max_tokens ≥ 8000`. > - **Reasoning text is in `message.reasoning`**, not `message.reasoning_content`. > - **MTP:** non-functional on stock vLLM, but reported working on ciprianveg's B12X sparse-MLA vLLM fork with `--draft-attention-backend B12X_MLA_SPARSE` (+48% decode on coding prompts). > - **1M context via decode-context-parallel is closed** on `glm_moe_dsa` in vLLM today (DSA indexer `k_cache` is replicated across DCP ranks while MLA KV is sharded → `page size is not divisible by target page size and cannot be padded` for `fp8_ds_mla`). Practical TP8 H200 ceiling: ~131K w/MTP, ~160K w/o. Pipeline-parallel (PP2 × TP4) profiles fine, but the MTP draft does not implement `SupportsPP`. **This is a CYBERSECURITY-DOMAIN CRACK of GLM-5.3-FP8 — not a general-purpose uncensor.**

译文排队中 · 当前显示来源原文

输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build

译文排队中 · 当前显示来源原文

输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build. Set > `fps`, which every build honours. > - **Pixel controls: use `mm_processor_kwargs.max_image_tokens` / `min_image_tokens`.** > `max_pixels`, `min_pixels`, `size` and `detail` return HTTP 200 and

译文排队中 · 当前显示来源原文

分类待补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗

> [!IMPORTANT] > **Serving note — read before your first request (vLLM / SGLang with a reasoning parser).** > > - **`reasoning_effort` only accepts `"low"` and `"high"`.** Anything else — `medium`, `xhigh`, > `off`, or omitting it — silently resolves to **`max`**, the deepest mode. Template line: > `reasoning_effort ... in ['low','high'] else 'max'`. > - **At `max`, a small `max_tokens` returns an EMPTY reply.** The model spends the whole budget > inside ` ` and you get `finish_reason="length"` with `content=""`. In multi-turn the empty > turn poisons the history and the conversation does not recover. Measured: `max` + `max_tokens > 2000` dies from turn ~4; `max` + `6000` is clean; `low` and `high` are clean at 2000. > **It is budget exhaustion, not a loop** — sampling changes do not rescue it. > - **Do NOT pass `enable_thinking`.** This template has no such variable (only `clear_thinking` and > `reasoning_effort`). Passing it — or a top-level `reasoning_effort: "none"` — turns the parser off > while the model still thinks, dumping raw reasoning into `content`. > - **Reasoning is returned in `message.reasoning`**, not `message.reasoning_content` > (vLLM renamed the output field; the input side still accepts both). > - `clear_thinking` must be nested inside `chat_template_kwargs` — a top-level key is ignored. > > > Use `"high"` for hard tasks; if you want `max`, give it `max_tokens >= 6000`. > > > **Video and image parameters — measured, because several are accepted then silently ignored.** > > - 🔴 **`media_io_kwargs.video.fps` must stay BELOW the clip's own frame rate.** Requesting a value > at or above it makes the placeholder builder count 3x the real tokens and **kills the engine**: > `ValueError: Attempted to assign N = N multimodal tokens to 3N placeholders` -> `EngineDeadError`, > server down until restarted. Upstream: vLLM #55644 / #55647. `fps: 2` is the safe, accurate choice. > - **`max_frames` and `num_frames` are not interchangeable across builds.** On vLLM nightly > `max_frames` is honoured and `num_frames` ignored; on the older `0.1.dev*` line it is the exact > reverse. A client that sets only one silently gets full-rate sampling on the other build

译文排队中 · 当前显示来源原文

分类待补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗
来源 / 文档 ↗
COST EXPLORER

好模型,也要算好成本。

费用分析

调整月度 Token 用量,直观比较不同模型的预估 API 开支。

1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价

使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照;不计缓存优惠、阶梯价、推理额外输出与税费,请以来源的当前报价为准。

MODEL HANDBOOK

读懂模型,再做选择

选型与常见问题
API 价格应该怎么比较?+

先区分输入、输出和缓存价格,再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费,不能直接与 Token 单价比较。

开放权重,就代表可以免费商用吗?+

不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。

排行榜第一,就是最适合我的模型吗?+

榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本,再选择模型。

AI NEWS · 从信息到选择

资讯看趋势,工具提效率,模型筑可能。

探索 AI 资讯 ↗发现 AI 工具 ↗