A **mixed-precision 4–6-bit quantization** of the multimodal projector (`mmproj` — the vision encoder and projector tensors) for `Qwen/Qwen3.8-27B`, built to be close to **a third of the size** of the upstream BF16 checkpoint (331 MiB vs 888 MiB) while staying within ~0.5% of its accuracy on an 11-benchmark vision suite. `Q5_K-MIX` is a mixed-precision quant that keeps the attention and FFN projections at 5-bit, holds the large FFN down-projection at 6-bit, and compresses the small vision-to-LM projectors hardest. The measured gap to the reference (net +18 failing documents, -0.0035 mean) is smaller than the run-to-run noise band the test protocol shows on reference-quality models, so we read it as within the measurement noise of the evaluation rather than a real degradation. Sub-4-bit variants of the same recipe were evaluated and showed regressions beyond that band, so the 5/6-bit mix is the smallest configuration that stayed within it on every benchmark. Both projectors served with `llama-server` against the `Qwen3.8-27B` target on a 24 GB NVIDIA GPU, evaluated with `lmms-eval` at temperature 0 (deterministic): 5,251 paired documents across 11 vision benchmarks (TextVQA, OCRBench-v2, GQA, ScienceQA, MMStar, ChartQA, and five BLINK perception categories), identical rows for both checkpoints.

Visual QA

Input Text · Image→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Hy-Memory-30B-A3B-MLX-Mixed4-6

hermitdave

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 ↗

LFM2.5-24B-A2B-MLX-DWQ-3bit

hermitdave

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 ↗

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

Gemma-4-26B-A4B-it-JANG_4M-GGUF

pixai-tagger-v1.0-onnx-1008-672-336-ft

Huihui-Qwen3-VL-32B-Instruct-FP8-abliterated

Qwen3.5-4B-GGUF

Kolibri-1-MLX-3bit

LFM-2.5-2.6B-heretic

LFM2.5-VL-3B-heretic

Qwen-3-VL-2B-Instruct-heretic

Qwen3-4B-Instruct-2507-heretic

Qwen3.8-27B-heretic-ara

voxtream2

Comfyui

dolphin-2.2.1-AshhLimaRP-Mistral-7B-GGUF

Llama-3.2-1B-Instruct-imatrix-GGUF

Llama-3-8B-Instruct-GGUF

Meta-Llama-3-70B-Instruct-GGUF

Mistral-7B-Instruct-v0.3-imatrix-GGUF

Phi-3-medium-128k-instruct-imatrix-GGUF

WizardLM-2-8x22B-imatrix-GGUF

Qwen3.6-35B-A3B-heretic-MTP-IQ4_XS-GGUF

Qwen3.8-27B-DFlash2-Q2_K_S-MIX-GGUF

Qwen3.8-27B-mmproj-Q5_K-MIX-GGUF

Hy-Memory-30B-A3B-MLX-Mixed4-6

LFM2.5-24B-A2B-MLX-DWQ-3bit

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.