Mixed-precision **GSQ-RCO** GGUF quantizations of TokenRhythm/NeoHorse-1-9B, optimized for efficient, high-fidelity local inference in `llama.cpp`. The model supports a context length of up to 262,144 tokens (262K). Standard quantization severely degrades hybrid SSM-Transformer models (e.g. stock low-bit quantizations cause recurrent state drift and degradation in reasoning coherence). **GSQ-RCO** solves this through two targeted techniques: - **RCO:** Keeps all 48 critical SSM parameters in unquantized **BF16**. - **GSQ:** Optimizes per-layer precision guided by Hessian sensitivity calibration.
Explore AI models 84999
Nex-N2.5-mini-GGUF
abenzerpsGGUF files for Nex-N2.5-mini, a long-context agentic model for coding, tool use, computer use, and multimodal workloads. The source checkpoint supports a native context length of **262,144 tokens (256K)**. *Benchmark results reported by Nex-AGI for the original Nex-N2.5 family. These figures are not measurements of this GGUF conversion.* The projector is optional for text-only use. Use it with a current llama.cpp build that supports the model's multimodal path.
Nex-N2.5-mini-MLX-4bit
abenzerps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
Ornith-1.5-9B-DFlash-GGUF
abenzerps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。
Ornith-1.5-9B-GSQ-RCO-GGUF
abenzerpsMixed-precision **GSQ-RCO** GGUF quantizations of ornith-ai/Ornith-1.5-9B, optimized for efficient, high-fidelity local inference in `llama.cpp`. The model supports a context length of up to 262,144 tokens (262K). Standard quantization severely degrades hybrid SSM-Transformer models (e.g. stock IQ3_M perplexity drops to ~75.2). **GSQ-RCO** solves this through two targeted techniques: - **RCO:** Keeps all 48 critical SSM parameters in unquantized **BF16**. - **GSQ:** Optimizes per-layer precision guided by Hessian sensitivity calibration.
Qwen-Image-2.1-Turbo-Quantized
abenzerpsGGUF, Safetensors, and MLX quantized formats of Qwen/Qwen-Image-2.1-Turbo for local image generation using the official turbo base weights. **Q4_K_M** is recommended for the best balance of size and quality for GGUF. **INT8 ConvRot** and **NVFP4** offer high performance on supported GPUs, while **MLX** formats are optimized for Apple Silicon. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository.
Qwen-Image-2.1-Uncensored-Quantized
abenzerpsGGUF, Safetensors, and MLX quantized formats of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. **Q4_K_M** is recommended for the best balance of size and quality for GGUF. **INT8 ConvRot** and **NVFP4** offer high performance on supported GPUs, while **MLX** formats are optimized for Apple Silicon. Use the model with ComfyUI and ComfyUI-GGUF.
Spark-X2.5-4B-GGUF
abenzerps> [!IMPORTANT] > **Compatibility:** These GGUF files require `llama.cpp` **b10828** or later, which includes official support for the Spark-X2.5 (`spark2_5`) architecture. Applications with a bundled runtime must use an equivalent or newer build. llama.cpp support GGUF quantizations of XHToken/Spark-X2.5-4B, a 4B general-purpose language model for reasoning, coding, tool use, and agentic workflows. Native context: **1,048,576 tokens (1M)**. Includes the upstream chat_template.jinja. Checksums: SHA256SUMS.txt.
Spark-X2.5-4B-MLX-4bit
abenzerps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
Spark-X2.5-4B-MLX-8bit
abenzerps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。
Spark-X2.6-4B-MLX-4bit
abenzerps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。
Spark-X2.6-4B-MLX-6bit
abenzerps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
Spark-X2.6-4B-MLX-8bit
abenzerps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
Spark-X2.6-4B-Quantized
abenzerps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
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。
ZDTaichu5.0-9B-GGUF
abenzerps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。
nanollava-gguf
abetlen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。
paligemma-3b-mix-224-gguf
abetlen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
Phi-3.5-vision-instruct-gguf
abetlen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
ophyx-350m-v2
abhash-chakraborty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
ARKA-SLM-V1
Abhayn01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
ARKA-v3-Multilingual-Pretrain
Abhayn01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
vllm-medusa-llama-68m-random
abhigoyal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。
qwen3-4b-terminal
AbhijitK20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
No matching models
Adjust provider, category or input/output filters. New models are added continuously.
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
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.
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.