Qwen3-VL-4B-Instruct-heretic-Q4_K_M-GGUF
matrixportalx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
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 85003
Turkish-Llama-8b-Instruct-v0.1-GGUF
matrixportalx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
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗X-Ray_Alpha-GGUF
matrixportalx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
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Devstral-Small-2-24B-AWQ
mattbucci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
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗gemma-4-12B-AWQ
mattbucciIn-house **AWQ-Marlin (4-bit)** quantization of `google/gemma-4-12B-it` — the encoder-free omni Gemma 4 (`Gemma4UnifiedForConditionalGeneration`): text + reasoning + tool-use + vision + audio, global-MQA attention, 5:1 sliding:full, ~262K native context. Packed **data-free** from the QAT base `google/gemma-4-12B-it-qat-q4_0-unquantized` (Gemma's quantization-aware-trained release). Because QAT already conditions the weights onto a 4-bit grid, a plain RTN re-quantization to AWQ group-128 is **near-lossless** — no calibration corpus needed: Weights are **5.4 GB/rank** at int4. Identical text quality to the BF16 base at matched context length.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗gemma-4-26B-AWQ
mattbucci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
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗gemma-4-31B-it-AutoRound-AWQ
mattbucci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
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-AWQ
mattbucci4-bit AWQ quantization of Qwen/Qwen3.8-27B, calibrated in-house on 2×RTX 3090 (Ampere, sm_86) for **single-user 256K-context serving under SGLang**. Thinking, image, and **video** are all preserved and probe-verified. Weights are ~18.7 GB, so the model fits two 24 GB cards at TP=2 with room for a deep KV pool (697K tokens measured at `--max-running 1`). Single-user decode throughput (M=1, 100 output tokens, depth server-verified via `actual_input_tokens`):
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-Flash-Next-W4A16-G128-300i
matteiuspi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
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-Flash-Next-W8A8-DYNAMIC-300i
matteiuspi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
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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。
Input Image→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗korean_sentiment
matthewburke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
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗gemma-4-E2B-it-crap-1.1-gguf
matthewhaynesonline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
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.5-0.8B-GGUF
matthewj-t6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。
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗antares-1b-GGUF
mattjoyce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
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗segformer_b0_clothes
mattmdjaga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
Input Image→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗segformer_b2_clothes
mattmdjagaSegFormer model fine-tuned on ATR dataset for clothes segmentation but can also be used for human segmentation. The dataset on hugging face is called "mattmdjaga/human_parsing_dataset". Labels: 0: "Background", 1: "Hat", 2: "Hair", 3: "Sunglasses", 4: "Upper-clothes", 5: "Skirt", 6: "Pants", 7: "Dress", 8: "Belt", 9: "Left-shoe", 10: "Right-shoe", 11: "Face", 12: "Left-leg", 13: "Right-leg", 14: "Left-arm", 15: "Right-arm", 16: "Bag", 17: "Scarf" Overall Evaluation Metrics: - Evaluation Loss: 0.15 - Mean Accuracy: 0.80 - Mean IoU: 0.69
Input Image→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗kokoro-coreml
mattmireles**15.1x faster than MLX on iPhone 15 Pro Max – while using 58% less RAM (1,338 MB vs 3,192 MB).** MLX was measured on the same iPhone, with the same text, same 27 sec audio duration. Kokoro-82M running on all three of Apple Silicon's key compute components (Neural Engine, GPU and CPU) through Core ML. No Python, no server, no API key. The model is cut into pieces at its seams, and each stage runs on the chip that suits it. That includes the vocoder, which the Neural Engine rejects as exported; a reshape that leaves its math unchanged gets it in. Warm median end-to-end time, token IDs in, 24 kHz audio out. Measured October 23, 2026 on the shipped pipeline, against MLX on the same device in the same session:
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DeepAnalyze-8B-Q4_K_M-GGUF
mattritchey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
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗next-1b-Q4_K_M-GGUF
mattritchey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。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Reflection-Llama-3.1-70B
mattshumer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。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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
Input Audio→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-DFlash2-NVFP4-RTNcal
maurienne-aiCalibrated **NVFP4 (W4A4)** quantization of the DFlash 2 block-diffusion draft model for **Qwen3.8-27B**, packaged in the NVIDIA ModelOpt layout that SGLang loads natively. Built for a single **RTX 5090 (32 GB)** serving Qwen3.8-27B in NVFP4 with SGLang: the draft shrinks from **3.53 GB (BF16) to 1.37 GB** of VRAM, which turns into **+44 % KV-cache context (90K → 130K tokens)** at the same decode speed and the same acceptance rate as the BF16 draft. Output quality is unchanged by construction: the target model verifies every drafted token. \* Target `gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090`, FP8 KV cache, `--mem-fraction-static 0.90`, HiCache on. Benchmark: 5 mixed prompts (code, math, French prose, JSON, essay) × 600 generated tokens, 3 runs each, temperature 0.7. Run-to-run noise on the acceptance length is about ±0.2, so BF16 and this checkpoint are at parity.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
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
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.