Filter by type:
Filter by tags:
qwen3-4b-dflash
Qwen3-4B paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend. This is the canonical DFlash pairing documented upstream (`z-lab/Qwen3-4B-DFlash` + `Qwen/Qwen3-4B`).
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The Q4_K_M file carries the full Qwen3-4B target; the ~0.5 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0 (Qwen3-4B target) / MIT (z-lab DFlash drafter).
Repository: localaiLicense: apache-2.0
qwen3.5-4b-dflash
Qwen3.5-4B paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend.
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The Q4_K_M file carries the full Qwen3.5-4B target; the ~0.6 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0 (Qwen3.5-4B target) / MIT (z-lab DFlash drafter).
Repository: localaiLicense: apache-2.0
qwen3.5-9b-dflash
Qwen3.5-9B paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend.
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The Q4_K_M file carries the full Qwen3.5-9B target; the ~1 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0 (Qwen3.5-9B target) / MIT (z-lab DFlash drafter).
Repository: localaiLicense: apache-2.0
qwen3.6-27b-dflash
Qwen3.6-27B (dense) paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend. DFlash gives its largest speedups on dense targets like this one.
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The Q4_K_M file carries the full Qwen3.6-27B target; the ~1.8 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0.
Repository: localaiLicense: apache-2.0
qwen3.6-35b-a3b-dflash
Qwen3.6-35B-A3B (Mixture-of-Experts, ~3B active per token) paired with its DFlash block-diffusion drafter for speculative decoding on the llama.cpp backend. DFlash speedups on MoE targets are smaller than on dense models, but still useful.
DFlash produces a whole block of draft tokens in a single forward pass and injects the target model's hidden states into the drafter's attention, which keeps the drafter tiny while making drafting GPU-friendly. The UD-Q4_K_M file carries the full Qwen3.6-35B-A3B target; the ~0.4 GB Q8_0 drafter (`draft-dflash`) accelerates generation without changing the target's outputs. The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here.
Flash attention is required for DFlash and is enabled in this config. A GPU is recommended.
License: Apache 2.0.
Repository: localaiLicense: apache-2.0
gemma-4-e4b-hauhaucs-aggressive-q4
HauhauCS Aggressive is an uncensored derivative of Google's Gemma 4 E4B
instruction model. This Q4_K_M GGUF supports text chat and image input
through the publisher's bundled F16 multimodal projector.
Uses the embedded chat template and the publisher's sampling settings.
The default context is 8192 tokens. The publisher declares the Gemma license.
Repository: localaiLicense: gemma
gemma-4-e4b-hauhaucs-aggressive-q5
HauhauCS Aggressive is an uncensored derivative of Google's Gemma 4 E4B
instruction model. This Q5_K_M GGUF supports text chat and image input
through the publisher's bundled F16 multimodal projector.
Uses the embedded chat template and the publisher's sampling settings.
The default context is 8192 tokens. The publisher declares the Gemma license.
Repository: localaiLicense: gemma
gemma-4-e2b-it-qat-mtp
Gemma 4 E2B IT QAT (Google DeepMind) paired with its Multi-Token Prediction (MTP) drafter head for speculative decoding on the llama.cpp backend. The Q4_K_XL target carries the full multimodal (text + image) model; the small `mtp-gemma-4-E2B-it` head predicts several tokens ahead which the target verifies in parallel, accelerating generation with no change to output quality. E2B is a MatFormer "effective 2B" elastic variant, well suited to lightweight and on-device deployments.
The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here. It uses the upstream `gemma4-assistant` architecture registered by llama.cpp PR #23398, so it loads on stock llama.cpp without any patch.
License: Apache 2.0 | Authors: Google DeepMind (target/drafter checkpoints), Unsloth (GGUF conversion)
Repository: localaiLicense: apache-2.0
gemma-4-e4b-it-qat-mtp
Gemma 4 E4B IT QAT (Google DeepMind) paired with its Multi-Token Prediction (MTP) drafter head for speculative decoding on the llama.cpp backend. The Q4_K_XL target carries the full multimodal (text + image) model; the small `mtp-gemma-4-E4B-it` head predicts several tokens ahead which the target verifies in parallel, accelerating generation with no change to output quality. E4B is a MatFormer "effective 4B" elastic variant, balancing quality and footprint for on-device and edge deployments.
The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here. It uses the upstream `gemma4-assistant` architecture registered by llama.cpp PR #23398, so it loads on stock llama.cpp without any patch.
License: Apache 2.0 | Authors: Google DeepMind (target/drafter checkpoints), Unsloth (GGUF conversion)
Repository: localaiLicense: apache-2.0
gemma-4-12b-it-qat-mtp
Gemma 4 12B IT QAT (Google DeepMind) paired with its Multi-Token Prediction (MTP) drafter head for speculative decoding on the llama.cpp backend. The Q4_K_XL target carries the full multimodal (text + image) model; the small `mtp-gemma-4-12B-it` head predicts several tokens ahead which the target verifies in parallel, accelerating generation with no change to output quality. As a dense model, Gemma 4 12B is among the sizes that benefit most from MTP, with the llama.cpp PR reporting well over 1.4x decode speedup.
The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here. It uses the upstream `gemma4-assistant` architecture registered by llama.cpp PR #23398, so it loads on stock llama.cpp without any patch.
License: Apache 2.0 | Authors: Google DeepMind (target/drafter checkpoints), Unsloth (GGUF conversion)
Repository: localaiLicense: apache-2.0
gemma-4-31b-it-qat-mtp
Gemma 4 31B IT QAT (Google DeepMind), the largest dense model in the family, paired with its Multi-Token Prediction (MTP) drafter head for speculative decoding on the llama.cpp backend. The Q4_K_XL target carries the full multimodal (text + image) model; the small `mtp-gemma-4-31B-it` head predicts several tokens ahead which the target verifies in parallel, accelerating generation with no change to output quality. Dense models like 31B are the sizes that benefit most from MTP.
The drafter is not a standalone chat model: it only runs paired with the target, which is why both are bundled here. It uses the upstream `gemma4-assistant` architecture registered by llama.cpp PR #23398, so it loads on stock llama.cpp without any patch.
License: Apache 2.0 | Authors: Google DeepMind (target/drafter checkpoints), Unsloth (GGUF conversion)
Repository: localaiLicense: apache-2.0
carnice-v2-27b
# Carnice-V2-27B for Hermes Agent
Carnice-V2-27B is a full merged BF16 SFT of `Qwen/Qwen3.6-27B` for Hermes-style agent traces. This repository contains the standalone merged model weights, not only a LoRA adapter.
## BF16 Transformers Loading Fix
The BF16 safetensors were republished with corrected `Qwen3_5ForConditionalGeneration` tensor prefixes. The original merge artifact accidentally serialized an extra Unsloth wrapper prefix, which caused direct HF Transformers loads to report the real weights as unexpected keys and initialize expected layers randomly. GGUF files were not affected because the GGUF conversion path normalized those prefixes.
## Benchmarks
The benchmark artifact bundle is included under `benchmarks/`. It contains the rendered graph, extracted `metrics.json`, benchmark scripts, and raw result files used to make the chart.
Scope note: the IFEval run is a short `limit=20` A/B smoke benchmark, not an official full leaderboard score. Held-out loss/perplexity is the exact assistant-only training-format validation metric from the SFT script. The raw BFCL two-case smoke files are included for auditability, but they are too small to use as a model-quality claim.
...
Repository: localaiLicense: apache-2.0
qwen3-omni-30b-a3b-instruct
Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation model. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. This GGUF build runs on llama.cpp with the bundled mmproj for multimodal inputs.
Repository: localaiLicense: apache-2.0
qwen3-omni-30b-a3b-thinking
Qwen3-Omni-30B-A3B-Thinking is the reasoning-enhanced variant of Qwen3-Omni, a natively end-to-end multilingual omni-modal foundation model. It processes text, images, and audio and produces chain-of-thought reasoning before the final answer. This GGUF build runs on llama.cpp with the bundled mmproj.
Repository: localaiLicense: apache-2.0
glm-ocr
GLM-OCR is a vision-language model specialized for optical character recognition and document understanding, built on the GLM architecture. This GGUF build runs on llama.cpp with the bundled mmproj.
Repository: localaiLicense: mit
hunyuan-ocr-q8
HunyuanOCR is Tencent's lightweight vision-language model for document parsing, text spotting, information extraction, and text-image translation. This Q8_0 GGUF build runs on llama.cpp with its bundled vision projector.
Repository: localaiLicense: tencent-hunyuan-community
deepseek-ocr
DeepSeek-OCR is a vision-language model from DeepSeek AI specialized for optical character recognition and document understanding. This GGUF build runs on llama.cpp with the bundled mmproj.
Repository: localaiLicense: mit
ideogram-4-iq4nl-ggml
Ideogram 4 is a text-to-image diffusion model known for state-of-the-art prompt adherence and exceptional, accurate text rendering inside images. It is driven by a Qwen3-VL-8B text encoder and performs real classifier-free guidance from a separate unconditional diffusion model.
This is the iQ4_NL (4-bit) quantization, a good balance of quality and footprint (~5.8GB diffusion + ~5.8GB unconditional). The bundle also pulls the Qwen3-VL-8B-Instruct text encoder and the FLUX.2 VAE. Quantized GGUF weights by stduhpf for use with stable-diffusion.cpp.
Repository: localaiLicense: ideogram-non-commercial-model-agreement
ideogram-4-q8_0-ggml
Ideogram 4 is a text-to-image diffusion model known for state-of-the-art prompt adherence and exceptional, accurate text rendering inside images. It is driven by a Qwen3-VL-8B text encoder and performs real classifier-free guidance from a separate unconditional diffusion model.
This is the Q8_0 (8-bit) quantization for highest quality (~10.1GB diffusion + ~10.1GB unconditional). The bundle also pulls the Qwen3-VL-8B-Instruct text encoder and the FLUX.2 VAE. Quantized GGUF weights by stduhpf for use with stable-diffusion.cpp.
Repository: localaiLicense: ideogram-non-commercial-model-agreement
qwen-image-2.1-q4_k-ggml
Qwen-Image 2.1 is the Qwen image generation foundation model, with strong prompt adherence and accurate text rendering (English and Chinese). It uses Qwen3-VL-8B as the text encoder and its own VAE, and supports both text-to-image and image editing: pass reference images to edit them.
This is the Q4_K (4-bit) quantization (~4.2GB diffusion model) by leejet for stable-diffusion.cpp. The bundle also pulls the Qwen3-VL-8B-Instruct text encoder with its vision projector (used for image editing) and the Qwen-Image 2.1 VAE. Use image dimensions divisible by 32.
Repository: localaiLicense: qwen-research
qwen-image-2.1-q8_0-ggml
Qwen-Image 2.1 is the Qwen image generation foundation model, with strong prompt adherence and accurate text rendering (English and Chinese). It uses Qwen3-VL-8B as the text encoder and its own VAE, and supports both text-to-image and image editing: pass reference images to edit them.
This is the Q8_0 (8-bit) quantization (~7.7GB diffusion model) by leejet for stable-diffusion.cpp. The bundle also pulls the Qwen3-VL-8B-Instruct text encoder with its vision projector (used for image editing) and the Qwen-Image 2.1 VAE. Use image dimensions divisible by 32.
Repository: localaiLicense: qwen-research
Page 1