Instructions to use NagusameCS/ultratensor-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use NagusameCS/ultratensor-models with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf NagusameCS/ultratensor-models # Run inference directly in the terminal: llama cli -hf NagusameCS/ultratensor-models
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf NagusameCS/ultratensor-models # Run inference directly in the terminal: llama cli -hf NagusameCS/ultratensor-models
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf NagusameCS/ultratensor-models # Run inference directly in the terminal: ./build/bin/llama cli -hf NagusameCS/ultratensor-models
Use Docker
docker model run hf.co/NagusameCS/ultratensor-models
- Llama new
- LM Studio
- Jan
- Ollama
How to use NagusameCS/ultratensor-models with Ollama:
ollama run hf.co/NagusameCS/ultratensor-models
- Unsloth Desktop
- Docker Model Runner
How to use NagusameCS/ultratensor-models with Docker Model Runner:
docker model run hf.co/NagusameCS/ultratensor-models
- Lemonade
How to use NagusameCS/ultratensor-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NagusameCS/ultratensor-models
Run and chat with the model
lemonade run user.ultratensor-models-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download model_catalog.json from NagusameCS/ultratensor-models: direct link, hf CLI and curl.
- Browser
- Download file 4.31 kB
-
https://huggingface.co/NagusameCS/ultratensor-models/resolve/main/model_catalog.json
- Command line
-
hf download hf://NagusameCS/ultratensor-models/model_catalog.json
-
curl -L -o model_catalog.json https://huggingface.co/NagusameCS/ultratensor-models/resolve/main/model_catalog.json
4.31 kB
| { | |
| "note": "UltraTensor expert splices of DeepSeek-V4-Pro, corrected release. Every file loads in stock llama.cpp.", | |
| "models": [ | |
| { | |
| "id": "keep12u", | |
| "file": "DeepSeek-V4-Coder-keep12u.gguf", | |
| "bytes": 34534261376, | |
| "sha256": "06fefca1eed7b65672f0b32fb35cf7b188a7b0f3b7d21ee8327be949a27dea36", | |
| "quant": "Q3_K_M", | |
| "quality_vs_full_model": { | |
| "code": { | |
| "mean_ppl_ratio": 7.841408, | |
| "mean_kld": 2.218059, | |
| "p99_kld": 10.272367, | |
| "max_kld": 12.204142, | |
| "same_top_p": 53.333, | |
| "ppl_q": 19.465803, | |
| "ppl_base": 2.482437, | |
| "mean_ln_ppl_ratio": 2.059418, | |
| "seconds": 525.6142222881317 | |
| }, | |
| "math": { | |
| "mean_ppl_ratio": 22.31243, | |
| "mean_kld": 3.286373, | |
| "p99_kld": 10.435582, | |
| "max_kld": 13.650668, | |
| "same_top_p": 31.046, | |
| "ppl_q": 99.04604, | |
| "ppl_base": 4.439052, | |
| "mean_ln_ppl_ratio": 3.105144, | |
| "seconds": 528.5378923416138 | |
| }, | |
| "web": { | |
| "mean_ppl_ratio": 17.845013, | |
| "mean_kld": 3.171519, | |
| "p99_kld": 10.442831, | |
| "max_kld": 13.924657, | |
| "same_top_p": 30.458, | |
| "ppl_q": 96.891198, | |
| "ppl_base": 5.429595, | |
| "mean_ln_ppl_ratio": 2.881724, | |
| "seconds": 686.1306977272034 | |
| }, | |
| "multilingual": { | |
| "mean_ppl_ratio": 118.08222, | |
| "mean_kld": 4.848422, | |
| "p99_kld": 11.466878, | |
| "max_kld": 14.286267, | |
| "same_top_p": 21.83, | |
| "ppl_q": 219.882016, | |
| "ppl_base": 1.862109, | |
| "mean_ln_ppl_ratio": 4.771381, | |
| "seconds": 401.41162276268005 | |
| } | |
| } | |
| }, | |
| { | |
| "id": "keep16u", | |
| "file": "DeepSeek-V4-Coder-keep16u.gguf", | |
| "bytes": 42213890208, | |
| "sha256": "41029742c93e00d408b2457030d278f733301605dad34bc8a7c87aa8016bf4f0", | |
| "quant": "Q3_K_M", | |
| "quality_vs_full_model": { | |
| "code": { | |
| "mean_ppl_ratio": 7.168135, | |
| "mean_kld": 2.13235, | |
| "p99_kld": 10.19467, | |
| "max_kld": 14.657751, | |
| "same_top_p": 54.641, | |
| "ppl_q": 17.794445, | |
| "ppl_base": 2.482437, | |
| "mean_ln_ppl_ratio": 1.969645, | |
| "seconds": 631.4457876682281 | |
| }, | |
| "math": { | |
| "mean_ppl_ratio": 22.87252, | |
| "mean_kld": 3.308744, | |
| "p99_kld": 10.898163, | |
| "max_kld": 13.628518, | |
| "same_top_p": 31.503, | |
| "ppl_q": 101.532307, | |
| "ppl_base": 4.439052, | |
| "mean_ln_ppl_ratio": 3.129936, | |
| "seconds": 536.8725681304932 | |
| }, | |
| "web": { | |
| "mean_ppl_ratio": 18.346225, | |
| "mean_kld": 3.201119, | |
| "p99_kld": 10.421721, | |
| "max_kld": 16.939787, | |
| "same_top_p": 31.242, | |
| "ppl_q": 99.612575, | |
| "ppl_base": 5.429595, | |
| "mean_ln_ppl_ratio": 2.909424, | |
| "seconds": 334.2714147567749 | |
| }, | |
| "multilingual": { | |
| "mean_ppl_ratio": 129.930837, | |
| "mean_kld": 4.94709, | |
| "p99_kld": 12.194567, | |
| "max_kld": 14.88663, | |
| "same_top_p": 21.111, | |
| "ppl_q": 241.945437, | |
| "ppl_base": 1.862109, | |
| "mean_ln_ppl_ratio": 4.867002, | |
| "seconds": 311.27877616882324 | |
| } | |
| } | |
| }, | |
| { | |
| "id": "keep16u-iq2xs", | |
| "file": "DeepSeek-V4-Coder-keep16u-iq2xs.gguf", | |
| "bytes": 30160640544, | |
| "sha256": "ab534a1b2f87dfc64edc42f68a33f45592c2d3f85f46a0f0aee46a5c6975b855", | |
| "quant": "IQ2_XS experts + Q3_K_M", | |
| "quality_vs_full_model": { | |
| "code": { | |
| "mean_ppl_ratio": 9.099898, | |
| "mean_kld": 2.362374, | |
| "p99_kld": 11.31906, | |
| "max_kld": 16.148975, | |
| "same_top_p": 53.137, | |
| "ppl_q": 22.589925, | |
| "ppl_base": 2.482437, | |
| "mean_ln_ppl_ratio": 2.208263, | |
| "seconds": 853.555673122406 | |
| }, | |
| "math": { | |
| "mean_ppl_ratio": 26.888559, | |
| "mean_kld": 3.447439, | |
| "p99_kld": 11.441486, | |
| "max_kld": 15.993463, | |
| "same_top_p": 30.654, | |
| "ppl_q": 119.359712, | |
| "ppl_base": 4.439052, | |
| "mean_ln_ppl_ratio": 3.291701, | |
| "seconds": 991.8521473407745 | |
| }, | |
| "web": { | |
| "mean_ppl_ratio": 20.035827, | |
| "mean_kld": 3.298229, | |
| "p99_kld": 10.33832, | |
| "max_kld": 15.200585, | |
| "same_top_p": 30.98, | |
| "ppl_q": 108.786426, | |
| "ppl_base": 5.429595, | |
| "mean_ln_ppl_ratio": 2.997522, | |
| "seconds": 978.4559774398804 | |
| }, | |
| "multilingual": { | |
| "mean_ppl_ratio": 143.609144, | |
| "mean_kld": 5.05533, | |
| "p99_kld": 12.383608, | |
| "max_kld": 15.366625, | |
| "same_top_p": 20.261, | |
| "ppl_q": 267.415942, | |
| "ppl_base": 1.862109, | |
| "mean_ln_ppl_ratio": 4.967095, | |
| "seconds": 965.1823761463165 | |
| } | |
| } | |
| } | |
| ] | |
| } |