MODEL PROFILE

clef-flash-GGUF

NANI-Nithin · clef-flash-GGUF

Cloudflare/clef-flash quantized for llama.cpp. The source is a 9.4B-parameter model (architecture `Qwen3_5ForConditionalGeneration`, 32 layers, hidden size 4096, vocab 248,320), post-trained by Cloudflare from Qwen/Qwen3.5-9B and released under Apache-2.0. This repo has 30 verified files: 29 GGUF quants plus the full-precision BF16 source. Clef-Flash is a **decision model**: it reads a state (text, JSON, images, or video) plus a schema of typed questions and returns a probability for every allowed option of every question in a single forward pass — no free-form text generation, no output parsing. That behavior comes from a backbone plus a separate **joint schema head** (and optionally the vision encoder). For the full decision-model behavior, use Cloudflare/clef-flash directly with `transformers` (5.10.2) and `torch` (2.11) per its README. What you get from this repo in llama.cpp is the post-trained Qwen3.5-9B language tower.

license:apache-2.0
Context windowNot disclosed
Input → Output待核验 → 待核验
Model weightsNot verified
Profile updated2026/11/2 19:16:02
OVERVIEW

Model overview

Cloudflare/clef-flash quantized for llama.cpp. The source is a 9.4B-parameter model (architecture `Qwen3_5ForConditionalGeneration`, 32 layers, hidden size 4096, vocab 248,320), post-trained by Cloudflare from Qwen/Qwen3.5-9B and released under Apache-2.0. This repo has 30 verified files: 29 GGUF quants plus the full-precision BF16 source. Clef-Flash is a **decision model**: it reads a state (text, JSON, images, or video) plus a schema of typed questions and returns a probability for every allowed option of every question in a single forward pass — no free-form text generation, no output parsing. That behavior comes from a backbone plus a separate **joint schema head** (and optionally the vision encoder). For the full decision-model behavior, use Cloudflare/clef-flash directly with `transformers` (5.10.2) and `torch` (2.11) per its README. What you get from this repo in llama.cpp is the post-trained Qwen3.5-9B language tower.

Key features

特点摘要待依据来源补齐,不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
No verified prices yet. Check the source channel.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。