> Note from hamish: This model its chat template altered to perserve intermediate thinking. > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.

Visual QA

Input Text · Image→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Qwen3.5-9B

hamishivi

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。

Visual QA

Input Text · Image→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Swift-1.5-Qwen3.8-27B-W4A16-RTX3090-NInfer-v3

hamixdd

Self-contained **NInfer** artifact for **Swift-1.5-Qwen3.8-27B** (fine-tune on the Qwen3.8-27B base), quantized to **groupwise W4A16** and tuned for the **NVIDIA RTX 3090 (24 GB, Ampere sm_86)**. Built for the **new NInfer generation** (v3 artifact format). For the engine itself, its options and profiles, see ashalliants/ninfer-3090. This is how the artifact was run and benchmarked on the RTX 3090 (172,032-token context, DFlash2 K=7 + draft head, cuBLAS prefill chunk 4096, 4 host-state slots, vision max-merged 2048):

Visual QA

Input Text · Image→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Qwen3.8-27B-GGUF

hammadRahman

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。

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

hamo-score-0.6b

HamoAI

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。

Text generation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

gemma-2-Ifable-9B-i1-GGUF

Hampetiudo

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 ↗

CompareSource / docs ↗

roberta-fake-news-classification

hamzab

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。

Text analysis

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

Monthly input tokens 10 MMonthly output tokens 2 M1 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.

Find your ideal AI model.

Explore AI models 84999

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-gliding_webbed_porcupine

turkish-pii-detection

turkish-pii-detection-GGUF

bubo-qwen3.8-flash-next

bubo-qwen3.8-flash-next-lower-memory

rwkv-weights

MiniMax-H3-Turbo-Lora-ComfyUI

Qwen3.8-27B-W4A16-Merlin

Qwen3.8-Flash-Next-W4A16-Merlin

Swift1.5-Qwen3.8-Flash-Next-W4A16-Merlin

ThinkingCap-Qwen3.8-27B-W4A16-Merlin

HM1

whisper-finetuned-somali-stt

Swap_face

Qwen3.8-27B-NVFP4-RTX5090-LMHead4

MOSS-TTS-Realtime-Persian-lora

Qwen3.5-2B

Qwen3.5-4B

Qwen3.5-9B

Swift-1.5-Qwen3.8-27B-W4A16-RTX3090-NInfer-v3

Qwen3.8-27B-GGUF

hamo-score-0.6b

gemma-2-Ifable-9B-i1-GGUF

roberta-fake-news-classification

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.