Model Gallery

Discover and install AI models from our curated collection

61 models available
1 repositories
Documentation

Find Your Perfect Model

Filter by Model Type

Browse by Tags

deepseek-v4.1-flash-ista-iq1_m
DeepSeek-V4.1-Flash-1017, a 763B-parameter mixture-of-experts model (384 experts per layer, 6 used per token), in ISTA-DAS's 1.75 bits per weight GSQ-RCO quantization (IQ1_M), the smallest size of the three (about 239 GB to download). It writes a reasoning trace before the answer, and the Strata backend splits it from the reply and parses the model's DSML tool calls. Text only: images are not supported by this backend. Needs a GPU with 12 GB of VRAM or more and about 34 GB of RAM at the least (Strata's figure; its measurements use 46 to 64 GB: an RTX 5070 with 64 GB answered at about 5 tokens per second, an RTX 3060 with 46 GB at 8 to 10). Less RAM still runs, slowly. Slightly lower quality than 2.00 bpw, and noticeably weaker on plain English prose; ISTA-DASLab measured 98.7% of the base model on its task average (AIME25, GPQA-Diamond, LiveCodeBench v6). Needs about 240 GB of free disk, on a fast NVMe drive: the 111 GB n-gram table (Engram) stays on disk and is read for every token. The Engram table and the 8 GB DSpark draft model are shared by all DeepSeek-V4.1 entries and downloaded once into strata/models/deepseek-v4.1-flash-shared. Runs only on the experimental strata backend, on NVIDIA CUDA 13 (x86_64 and arm64), AMD Radeon RX 9070 and R9700 (ROCm) and Apple Silicon (Metal). Strata ships no DeepSeek engine for CUDA 12, Intel or other AMD cards. On the first load the strata backend builds the Strata pack from the GGUF files (under a minute, a few MB of extra disk); loading the model afterwards takes a few minutes. The default context is 8192 tokens, the size Strata checked; raise context_size if the GPU has room. Licensed under the MIT License (DeepSeek-V4.1-Flash-1017 and the quantized files). The GGUF files are the GSQ-RCO quantization by ISTA-DAS (ISTA-DASLab); the DSpark draft model is Unsloth's; Strata is by Niko1221.

Repository: localaiLicense: mit

deepseek-v4.1-flash-ista-iq2_xxs
DeepSeek-V4.1-Flash-1017, a 763B-parameter mixture-of-experts model (384 experts per layer, 6 used per token), in ISTA-DAS's 2.00 bits per weight GSQ-RCO quantization (IQ2_XXS), the middle size of the three (about 257 GB to download). It writes a reasoning trace before the answer, and the Strata backend splits it from the reply and parses the model's DSML tool calls. Text only: images are not supported by this backend. Needs a GPU with 12 GB of VRAM or more and about 40 GB of RAM at the least (Strata's figure; its measurements use 46 to 64 GB: an RTX 5070 with 64 GB answered at about 5 tokens per second, an RTX 3060 with 46 GB at 8 to 10). Less RAM still runs, slowly. Strata measured a perplexity 15.5% above the original model on 4,995 positions (code 8.6%, agent work 5.3%). Needs about 258 GB of free disk, on a fast NVMe drive: the 111 GB n-gram table (Engram) stays on disk and is read for every token. The Engram table and the 8 GB DSpark draft model are shared by all DeepSeek-V4.1 entries and downloaded once into strata/models/deepseek-v4.1-flash-shared. Runs only on the experimental strata backend, on NVIDIA CUDA 13 (x86_64 and arm64), AMD Radeon RX 9070 and R9700 (ROCm) and Apple Silicon (Metal). Strata ships no DeepSeek engine for CUDA 12, Intel or other AMD cards. On the first load the strata backend builds the Strata pack from the GGUF files (under a minute, a few MB of extra disk); loading the model afterwards takes a few minutes. The default context is 8192 tokens, the size Strata checked; raise context_size if the GPU has room. Licensed under the MIT License (DeepSeek-V4.1-Flash-1017 and the quantized files). The GGUF files are the GSQ-RCO quantization by ISTA-DAS (ISTA-DASLab); the DSpark draft model is Unsloth's; Strata is by Niko1221.

Repository: localaiLicense: mit

deepseek-v4.1-flash-ista-iq2_xs
DeepSeek-V4.1-Flash-1017, a 763B-parameter mixture-of-experts model (384 experts per layer, 6 used per token), in ISTA-DAS's 2.25 bits per weight GSQ-RCO quantization (IQ2_XS), the largest size of the three (about 274 GB to download). It writes a reasoning trace before the answer, and the Strata backend splits it from the reply and parses the model's DSML tool calls. Text only: images are not supported by this backend. Needs a GPU with 12 GB of VRAM or more and about 44 GB of RAM at the least (Strata's figure; its measurements use 46 to 64 GB: an RTX 5070 with 64 GB answered at about 5 tokens per second, an RTX 3060 with 46 GB at 8 to 10). Less RAM still runs, slowly. Strata measured a perplexity 7.3% above the original model on 4,995 positions (code 3.2%, agent work 2.2%). Needs about 275 GB of free disk, on a fast NVMe drive: the 111 GB n-gram table (Engram) stays on disk and is read for every token. The Engram table and the 8 GB DSpark draft model are shared by all DeepSeek-V4.1 entries and downloaded once into strata/models/deepseek-v4.1-flash-shared. Runs only on the experimental strata backend, on NVIDIA CUDA 13 (x86_64 and arm64), AMD Radeon RX 9070 and R9700 (ROCm) and Apple Silicon (Metal). Strata ships no DeepSeek engine for CUDA 12, Intel or other AMD cards. On the first load the strata backend builds the Strata pack from the GGUF files (under a minute, a few MB of extra disk); loading the model afterwards takes a few minutes. The default context is 8192 tokens, the size Strata checked; raise context_size if the GPU has room. Licensed under the MIT License (DeepSeek-V4.1-Flash-1017 and the quantized files). The GGUF files are the GSQ-RCO quantization by ISTA-DAS (ISTA-DASLab); the DSpark draft model is Unsloth's; Strata is by Niko1221.

Repository: localaiLicense: mit

deepseek-v4.1-flash-ista-coder-iq2_xxs
ISTA-DAS's coding version of DeepSeek-V4.1-Flash-1017: in every layer 192 of the 384 routed experts are kept and the other 192 removed, stored in the 2.00 bpw (IQ2_XXS) layout. It is the smallest DeepSeek-V4.1 set here (about 191 GB to download). It writes a reasoning trace before the answer, and the Strata backend splits it from the reply and parses the model's DSML tool calls. Text only: images are not supported by this backend. Needs a GPU with 12 GB of VRAM or more and about 24 GB of RAM at the least (Strata's figure; its measurements use 46 to 64 GB: an RTX 5070 with 64 GB answered at about 5 tokens per second, an RTX 3060 with 46 GB at 8 to 10). Less RAM still runs, slowly. Strata measured a perplexity 48% above the original model on its test set (KL 0.40), so it is weaker than the full sets on prose and general knowledge; it is meant for code and agent work. Needs about 192 GB of free disk, on a fast NVMe drive: the 111 GB n-gram table (Engram) stays on disk and is read for every token. The Engram table and the 8 GB DSpark draft model are shared by all DeepSeek-V4.1 entries and downloaded once into strata/models/deepseek-v4.1-flash-shared. Runs only on the experimental strata backend, on NVIDIA CUDA 13 (x86_64 and arm64), AMD Radeon RX 9070 and R9700 (ROCm) and Apple Silicon (Metal). Strata ships no DeepSeek engine for CUDA 12, Intel or other AMD cards. On the first load the strata backend builds the Strata pack from the GGUF files (under a minute, a few MB of extra disk); loading the model afterwards takes a few minutes. The default context is 8192 tokens, the size Strata checked; raise context_size if the GPU has room. Licensed under the MIT License (DeepSeek-V4.1-Flash-1017 and the quantized files). The GGUF files are the GSQ-RCO quantization by ISTA-DAS (ISTA-DASLab); the DSpark draft model is Unsloth's; Strata is by Niko1221.

Repository: localaiLicense: mit

voxtral-mini-4b-realtime
Voxtral Mini 4B Realtime is a speech-to-text model from Mistral AI. It is a 4B parameter model optimized for fast, accurate audio transcription with low latency, making it ideal for real-time applications. The model uses the Voxtral architecture for efficient audio processing.

Repository: localaiLicense: apache-2.0

ace-step-turbo
ACE-Step 1.5 Turbo is a music generation model that can create music from text descriptions, lyrics, or audio samples. Supports both simple text-to-music and advanced music generation with metadata like BPM, key scale, and time signature.

Repository: localaiLicense: mit

acestep-cpp-turbo-4b
ACE-Step 1.5 Turbo (C++ / GGML) with 4B LM — higher quality music generation from text and lyrics. Uses the larger 4B parameter LM for better metadata/code generation. Stereo 48kHz output.

Repository: localaiLicense: mit

face-detect-buffalo-l
Face recognition with insightface's `buffalo_l` pack (SCRFD-10GF detector + ResNet50 ArcFace 512-d embedder), ported to C++/ggml and shipped as a single GGUF for the `face-detect` backend. Highest accuracy of the buffalo line. No Python / onnxruntime / torch runtime: face-detect.cpp reads the detector and embedder architecture (`facedetect.arch`) directly from the GGUF metadata, so installing this entry is all that is needed to select buffalo_l. Drives the Embedding / Detect / FaceVerify / FaceAnalyze gRPC rpcs and the /v1/face/{verify,analyze,embed,detect} REST endpoints. This GGUF also embeds the MiniFASNet anti-spoof ensemble, available via the FaceVerify `anti_spoof` request flag. NON-COMMERCIAL RESEARCH USE ONLY: for commercial use see `face-detect-yunet-sface`.

Repository: localaiLicense: insightface-non-commercial

face-detect-buffalo-m
Face recognition with insightface's `buffalo_m` pack (SCRFD-2.5GF detector + ResNet50 ArcFace embedder), converted to a C++/ggml GGUF for the `face-detect` backend. Same recognition accuracy as `buffalo_l` with a cheaper detector: a good balance on mid-range hardware. The architecture (`facedetect.arch`) is read from the GGUF metadata, so this entry alone selects the buffalo_m engine. This GGUF also embeds the MiniFASNet anti-spoof ensemble, available via the FaceVerify `anti_spoof` request flag. NON-COMMERCIAL RESEARCH USE ONLY.

Repository: localaiLicense: insightface-non-commercial

face-detect-buffalo-s
Face recognition with insightface's `buffalo_s` pack (SCRFD-500MF detector + MBF 512-d embedder), converted to a C++/ggml GGUF for the `face-detect` backend. Small and CPU-friendly: a good fit for mid-range and edge deployments. The architecture (`facedetect.arch`) is read from the GGUF metadata, so this entry alone selects the buffalo_s engine. This GGUF also embeds the MiniFASNet anti-spoof ensemble, available via the FaceVerify `anti_spoof` request flag. NON-COMMERCIAL RESEARCH USE ONLY.

Repository: localaiLicense: insightface-non-commercial

face-detect-buffalo-sc
Face recognition with insightface's `buffalo_sc` pack (SCRFD-500M detector + a small ArcFace embedder), converted to a C++/ggml GGUF for the `face-detect` backend. This is the smallest insightface pack: the lightest option for low-resource and edge deployments. The architecture (`facedetect.arch`) is read from the GGUF metadata, so this entry alone selects the buffalo_sc engine. If this GGUF embeds the MiniFASNet anti-spoof ensemble, it is available via the FaceVerify `anti_spoof` request flag. NON-COMMERCIAL RESEARCH USE ONLY.

Repository: localaiLicense: insightface-non-commercial

face-detect-antelopev2
Face recognition with insightface's `antelopev2` pack (SCRFD-10G detector + ArcFace glint360k R100, 512-d embedder), converted to a C++/ggml GGUF for the `face-detect` backend. The higher-accuracy insightface pack: heavier, but the best fit when recognition quality matters more than speed. The architecture (`facedetect.arch`) is read from the GGUF metadata, so this entry alone selects the antelopev2 engine. If this GGUF embeds the MiniFASNet anti-spoof ensemble, it is available via the FaceVerify `anti_spoof` request flag. NON-COMMERCIAL RESEARCH USE ONLY.

Repository: localaiLicense: insightface-non-commercial

face-detect-yunet-sface
Face recognition with OpenCV Zoo weights: YuNet detector + SFace 128-d recognizer, converted to a C++/ggml GGUF for the `face-detect` backend. APACHE 2.0: safe for commercial use. Lower accuracy than the buffalo packs and no demographic head, but the commercial-friendly alternative to the insightface buffalo line. The architecture (`facedetect.arch`) is read from the GGUF metadata, so this entry alone selects the YuNet + SFace engine.

Repository: localaiLicense: apache-2.0

voice-detect-ecapa-tdnn
Speaker (voice) recognition with SpeechBrain's ECAPA-TDNN trained on VoxCeleb, ported to C++/ggml and shipped as a single GGUF for the `voice-detect` backend. 192-d L2-normalised embeddings, ~1.9% Equal Error Rate on VoxCeleb1-O. APACHE 2.0 - commercial-safe. No Python / torch runtime: voice-detect.cpp reads the embedding architecture (`voicedetect.arch`) directly from the GGUF metadata, so installing this entry is all that is needed to select ECAPA-TDNN. Drives the VoiceVerify / VoiceEmbed gRPC rpcs and the /v1/voice/{verify,embed,register,identify,forget} REST endpoints.

Repository: localaiLicense: apache-2.0

voice-detect-wespeaker-resnet34
Speaker recognition with WeSpeaker's ResNet34 trained on VoxCeleb, converted to a C++/ggml GGUF for the `voice-detect` backend. 256-d embeddings, CPU-friendly and runtime-free (no onnxruntime or torch). CC-BY-4.0. Use when you want WeSpeaker's ResNet34 topology instead of ECAPA-TDNN. The embedding architecture (`voicedetect.arch`) is read from the GGUF metadata, so this entry alone selects the engine.

Repository: localaiLicense: cc-by-4.0

voice-detect-eres2net
Speaker recognition with 3D-Speaker's ERes2Net trained on VoxCeleb, converted to a C++/ggml GGUF for the `voice-detect` backend. 192-d embeddings with strong verification accuracy. APACHE 2.0. The embedding architecture (`voicedetect.arch`) is read from the GGUF metadata, so this entry alone selects the ERes2Net engine.

Repository: localaiLicense: apache-2.0

voice-detect-campplus
Speaker recognition with 3D-Speaker's CAM++ trained on VoxCeleb, converted to a C++/ggml GGUF for the `voice-detect` backend. 192-d embeddings, a fast context-aware masking topology well-suited to CPU and edge deployments. APACHE 2.0. The embedding architecture (`voicedetect.arch`) is read from the GGUF metadata, so this entry alone selects the CAM++ engine.

Repository: localaiLicense: apache-2.0

voice-detect-emotion-wav2vec2
Voice analysis (age / gender / emotion) with audEERING's wav2vec2 model, converted to a C++/ggml GGUF for the `voice-detect` backend. Drives the VoiceAnalyze gRPC rpc and the /v1/voice/analyze REST endpoint, returning a continuous age estimate plus gender and emotion class scores for a single utterance. CC-BY-NC-SA-4.0 - research / non-commercial use only. The analysis architecture (`voicedetect.arch`) is read from the GGUF metadata, so this entry alone selects the wav2vec2 analyze head.

Repository: localaiLicense: cc-by-nc-sa-4.0

voice-detect-age-gender-wav2vec2
wav2vec2-large-robust age + gender analysis head (audeering/wav2vec2-large-robust-24-ft-age-gender), converted to a C++/ggml GGUF for the `voice-detect` backend. Drives the VoiceAnalyze gRPC rpc and the /v1/voice/analyze REST endpoint, returning a continuous age estimate plus gender class scores for a single utterance. CC-BY-NC-SA-4.0 - research / non-commercial use only. The analysis architecture (`voicedetect.arch`) is read from the GGUF metadata, so this entry alone selects the wav2vec2 analyze head.

Repository: localaiLicense: cc-by-nc-sa-4.0

google-gemma-3-27b-it-qat-q4_0-small
This is a requantized version of https://huggingface.co/google/gemma-3-27b-it-qat-q4_0-gguf. The official QAT weights released by google use fp16 (instead of Q6_K) for the embeddings table, which makes this model take a significant extra amount of memory (and storage) compared to what Q4_0 quants are supposed to take. Requantizing with llama.cpp achieves a very similar result. Note that this model ends up smaller than the Q4_0 from Bartowski. This is because llama.cpp sets some tensors to Q4_1 when quantizing models to Q4_0 with imatrix, but this is a static quant. The perplexity score for this one is even lower with this model compared to the original model by Google, but the results are within margin of error, so it's probably just luck. I also fixed the control token metadata, which was slightly degrading the performance of the model in instruct mode.

Repository: localaiLicense: gemma

meta-llama_llama-4-scout-17b-16e-instruct
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. These Llama 4 models mark the beginning of a new era for the Llama ecosystem. We are launching two efficient models in the Llama 4 series, Llama 4 Scout, a 17 billion parameter model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts.

Repository: localaiLicense: llama4

Page 1 of many