Instructions to use ModernoTech/Nova-Mini 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 ModernoTech/Nova-Mini 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 ModernoTech/Nova-Mini:Q4_K_M # Run inference directly in the terminal: llama cli -hf ModernoTech/Nova-Mini:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ModernoTech/Nova-Mini:Q4_K_M # Run inference directly in the terminal: llama cli -hf ModernoTech/Nova-Mini:Q4_K_M
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 ModernoTech/Nova-Mini:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf ModernoTech/Nova-Mini:Q4_K_M
Use Docker
docker model run hf.co/ModernoTech/Nova-Mini:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use ModernoTech/Nova-Mini with Ollama:
ollama run hf.co/ModernoTech/Nova-Mini:Q4_K_M
- Unsloth Desktop
- Pi
How to use ModernoTech/Nova-Mini with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ModernoTech/Nova-Mini:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ModernoTech/Nova-Mini:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ModernoTech/Nova-Mini with Docker Model Runner:
docker model run hf.co/ModernoTech/Nova-Mini:Q4_K_M
- Lemonade
How to use ModernoTech/Nova-Mini with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ModernoTech/Nova-Mini:Q4_K_M
Run and chat with the model
lemonade run user.Nova-Mini-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use ModernoTech/Nova-Mini with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ModernoTech/Nova-Mini:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default ModernoTech/Nova-Mini:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ModernoTech/Nova-Mini with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ModernoTech/Nova-Mini:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "ModernoTech/Nova-Mini:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Performance Lab phase 2: JSON, CSV, methodology, hardware reference, reproducible scripts and 7 PNG charts
2f54e3e verified Download performance/performance.json from ModernoTech/Nova-Mini: direct link, hf CLI and curl.
- Browser
- Download file 18.2 kB
-
https://huggingface.co/ModernoTech/Nova-Mini/resolve/main/performance/performance.json
- Command line
-
hf download hf://ModernoTech/Nova-Mini/performance/performance.json
-
curl -L -o performance.json https://huggingface.co/ModernoTech/Nova-Mini/resolve/main/performance/performance.json
18.2 kB
| { | |
| "title": "Nova Mini 1.0 performance lab", | |
| "status": "All numerical performance values are theoretical or not validated; no unverified benchmark is presented as measured", | |
| "status legend": { | |
| "MEDIDO": "physical measurement backed by a dated log and exact configuration", | |
| "ESTIMADO": "mathematical projection with its assumptions documented", | |
| "NO VALIDADO": "insufficient evidence or unavailable native configuration" | |
| }, | |
| "repository": "ModernoTech/Nova-Mini", | |
| "artifact": { | |
| "filename": "Nova-Mini-1.0-Q4_K_M.gguf", | |
| "bytes": 484220288, | |
| "sha256": "03a9f2b5eaa26e8a801012cf5c2eb75f2997da0725ce99bc03622d4bae583fdd", | |
| "format": "GGUF", | |
| "published": true, | |
| "source_of_size": "Hugging Face file metadata" | |
| }, | |
| "specs": { | |
| "model_name": "Nova Mini 1.0", | |
| "base_reference": "Qwen/Qwen3-0.6B", | |
| "total_params_billion": 0.6, | |
| "active_params_billion": 0.6, | |
| "moe": false, | |
| "max_position_documented": 40960 | |
| }, | |
| "architecture_basis": { | |
| "layers": 28, | |
| "kv_heads": 8, | |
| "head_dim": 128, | |
| "source": "Qwen config.json downloaded from the documented base reference", | |
| "status": "ESTIMADO sobre una arquitectura publicada de terceros" | |
| }, | |
| "estimation_assumptions": { | |
| "ram_bandwidth_values_gbps": { | |
| "MacBook Air 2014": 25.6, | |
| "Lenovo Yoga 720": 34.1, | |
| "MacBook Neo A18 Pro": 60.0, | |
| "MacBook Air M4": 120.0 | |
| }, | |
| "ssd_effective_gbps": 2.0, | |
| "ssd_basis": "Assumed external NVMe 2.0 GB/s for calculations only; must be replaced by a measured sequential/shared load if used externally", | |
| "kv_precision_bytes": 2.0, | |
| "weight_precision_bytes": 0.5, | |
| "overhead_factor": 1.1, | |
| "os_overhead_gb": 1.2, | |
| "runtime_overhead_bytes": 120.0, | |
| "latency_included": "Fixed read latency excluded; remeasurement is required before any availability claim", | |
| "mne_expert_cache_fraction": "Active set + capped additive cache; rounded, saturation assumptions stated", | |
| "conventional_write_notes": "Conventional RAM path counts total artifact weights resident in RAM; active path measures only the bytes read per token as an upper bound" | |
| }, | |
| "measured": null, | |
| "ssd_cache_scenarios": [ | |
| { | |
| "cache_hit": 0.9, | |
| "ssd_mne_upper_tok_s": 60.606 | |
| }, | |
| { | |
| "cache_hit": 0.95, | |
| "ssd_mne_upper_tok_s": 121.212 | |
| }, | |
| { | |
| "cache_hit": 0.99, | |
| "ssd_mne_upper_tok_s": 606.061 | |
| }, | |
| { | |
| "cache_hit": 0.995, | |
| "ssd_mne_upper_tok_s": 1212.121 | |
| }, | |
| { | |
| "cache_hit": 0.999, | |
| "ssd_mne_upper_tok_s": 6060.606 | |
| } | |
| ], | |
| "scenarios": [ | |
| { | |
| "model": "Nova Mini 1.0", | |
| "repository": "ModernoTech/Nova-Mini", | |
| "hardware": "MacBook Air 2014", | |
| "hardware_id": "air-2014", | |
| "bandwidth_gbps": 25.6, | |
| "ram_gb": 4.0, | |
| "context_tokens": 4096, | |
| "context_label": "4K", | |
| "context_supported_or_validated": true, | |
| "max_position_documented": 40960, | |
| "artifact_size_bytes": 484220288, | |
| "artifact_status": "PUBLICADO", | |
| "weight_basis": "artifact size on Hugging Face", | |
| "active_payload_bytes_for_memory_bound": 354334802, | |
| "active_payload_basis": "active param count x 0.5 GiB/B x 1.10 (Q4 + 10% parsed overhead), ESTIMADO", | |
| "theoretical_tok_s_conventional_ram": 77.576, | |
| "ssd_mne_upper_tok_s": [ | |
| { | |
| "ssd_cache_miss": 0.1, | |
| "cache_label": "90%", | |
| "upper Tok_s": 60.606 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.05, | |
| "cache_label": "95%", | |
| "upper Tok_s": 121.212 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.01, | |
| "cache_label": "99%", | |
| "upper Tok_s": 606.061 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.005, | |
| "cache_label": "99.5%", | |
| "upper Tok_s": 1212.121 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.001, | |
| "cache_label": "99.9%", | |
| "upper Tok_s": 6060.606 | |
| } | |
| ], | |
| "kv_cache_bytes_est": 469762048, | |
| "kv_cache_status": "ESTIMADO", | |
| "conventional_resident_total_gb_est": 1.005653, | |
| "mne_resident_total_gb_est": 1.370938, | |
| "ssd_required_bytes": 484220288, | |
| "feasible_conventional": "VIABLE con margen de memoria (límite superior de presión, no medición)", | |
| "feasible_mne": "ESCENARIO VIRTUOSO DE RAM (cache capado; no prueba de throughput)", | |
| "throughput_status": "ESTIMADO (techo de ancho de banda, no benchmark)", | |
| "throughput_note": "No real benchmark is stored for MNE; upper bounds only." | |
| }, | |
| { | |
| "model": "Nova Mini 1.0", | |
| "repository": "ModernoTech/Nova-Mini", | |
| "hardware": "Lenovo Yoga 720", | |
| "hardware_id": "yoga-720", | |
| "bandwidth_gbps": 34.1, | |
| "ram_gb": 8.0, | |
| "context_tokens": 4096, | |
| "context_label": "4K", | |
| "context_supported_or_validated": true, | |
| "max_position_documented": 40960, | |
| "artifact_size_bytes": 484220288, | |
| "artifact_status": "PUBLICADO", | |
| "weight_basis": "artifact size on Hugging Face", | |
| "active_payload_bytes_for_memory_bound": 354334802, | |
| "active_payload_basis": "active param count x 0.5 GiB/B x 1.10 (Q4 + 10% parsed overhead), ESTIMADO", | |
| "theoretical_tok_s_conventional_ram": 103.333, | |
| "ssd_mne_upper_tok_s": [ | |
| { | |
| "ssd_cache_miss": 0.1, | |
| "cache_label": "90%", | |
| "upper Tok_s": 60.606 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.05, | |
| "cache_label": "95%", | |
| "upper Tok_s": 121.212 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.01, | |
| "cache_label": "99%", | |
| "upper Tok_s": 606.061 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.005, | |
| "cache_label": "99.5%", | |
| "upper Tok_s": 1212.121 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.001, | |
| "cache_label": "99.9%", | |
| "upper Tok_s": 6060.606 | |
| } | |
| ], | |
| "kv_cache_bytes_est": 469762048, | |
| "kv_cache_status": "ESTIMADO", | |
| "conventional_resident_total_gb_est": 1.005653, | |
| "mne_resident_total_gb_est": 1.370938, | |
| "ssd_required_bytes": 484220288, | |
| "feasible_conventional": "VIABLE con margen de memoria (límite superior de presión, no medición)", | |
| "feasible_mne": "ESCENARIO VIRTUOSO DE RAM (cache capado; no prueba de throughput)", | |
| "throughput_status": "ESTIMADO (techo de ancho de banda, no benchmark)", | |
| "throughput_note": "No real benchmark is stored for MNE; upper bounds only." | |
| }, | |
| { | |
| "model": "Nova Mini 1.0", | |
| "repository": "ModernoTech/Nova-Mini", | |
| "hardware": "MacBook Neo A18 Pro", | |
| "hardware_id": "neo", | |
| "bandwidth_gbps": 60.0, | |
| "ram_gb": 8.0, | |
| "context_tokens": 4096, | |
| "context_label": "4K", | |
| "context_supported_or_validated": true, | |
| "max_position_documented": 40960, | |
| "artifact_size_bytes": 484220288, | |
| "artifact_status": "PUBLICADO", | |
| "weight_basis": "artifact size on Hugging Face", | |
| "active_payload_bytes_for_memory_bound": 354334802, | |
| "active_payload_basis": "active param count x 0.5 GiB/B x 1.10 (Q4 + 10% parsed overhead), ESTIMADO", | |
| "theoretical_tok_s_conventional_ram": 181.818, | |
| "ssd_mne_upper_tok_s": [ | |
| { | |
| "ssd_cache_miss": 0.1, | |
| "cache_label": "90%", | |
| "upper Tok_s": 60.606 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.05, | |
| "cache_label": "95%", | |
| "upper Tok_s": 121.212 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.01, | |
| "cache_label": "99%", | |
| "upper Tok_s": 606.061 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.005, | |
| "cache_label": "99.5%", | |
| "upper Tok_s": 1212.121 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.001, | |
| "cache_label": "99.9%", | |
| "upper Tok_s": 6060.606 | |
| } | |
| ], | |
| "kv_cache_bytes_est": 469762048, | |
| "kv_cache_status": "ESTIMADO", | |
| "conventional_resident_total_gb_est": 1.005653, | |
| "mne_resident_total_gb_est": 1.370938, | |
| "ssd_required_bytes": 484220288, | |
| "feasible_conventional": "VIABLE con margen de memoria (límite superior de presión, no medición)", | |
| "feasible_mne": "ESCENARIO VIRTUOSO DE RAM (cache capado; no prueba de throughput)", | |
| "throughput_status": "ESTIMADO (techo de ancho de banda, no benchmark)", | |
| "throughput_note": "No real benchmark is stored for MNE; upper bounds only." | |
| }, | |
| { | |
| "model": "Nova Mini 1.0", | |
| "repository": "ModernoTech/Nova-Mini", | |
| "hardware": "MacBook Air M4", | |
| "hardware_id": "air-m4", | |
| "bandwidth_gbps": 120.0, | |
| "ram_gb": 16.0, | |
| "context_tokens": 4096, | |
| "context_label": "4K", | |
| "context_supported_or_validated": true, | |
| "max_position_documented": 40960, | |
| "artifact_size_bytes": 484220288, | |
| "artifact_status": "PUBLICADO", | |
| "weight_basis": "artifact size on Hugging Face", | |
| "active_payload_bytes_for_memory_bound": 354334802, | |
| "active_payload_basis": "active param count x 0.5 GiB/B x 1.10 (Q4 + 10% parsed overhead), ESTIMADO", | |
| "theoretical_tok_s_conventional_ram": 363.636, | |
| "ssd_mne_upper_tok_s": [ | |
| { | |
| "ssd_cache_miss": 0.1, | |
| "cache_label": "90%", | |
| "upper Tok_s": 60.606 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.05, | |
| "cache_label": "95%", | |
| "upper Tok_s": 121.212 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.01, | |
| "cache_label": "99%", | |
| "upper Tok_s": 606.061 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.005, | |
| "cache_label": "99.5%", | |
| "upper Tok_s": 1212.121 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.001, | |
| "cache_label": "99.9%", | |
| "upper Tok_s": 6060.606 | |
| } | |
| ], | |
| "kv_cache_bytes_est": 469762048, | |
| "kv_cache_status": "ESTIMADO", | |
| "conventional_resident_total_gb_est": 1.005653, | |
| "mne_resident_total_gb_est": 1.370938, | |
| "ssd_required_bytes": 484220288, | |
| "feasible_conventional": "VIABLE con margen de memoria (límite superior de presión, no medición)", | |
| "feasible_mne": "ESCENARIO VIRTUOSO DE RAM (cache capado; no prueba de throughput)", | |
| "throughput_status": "ESTIMADO (techo de ancho de banda, no benchmark)", | |
| "throughput_note": "No real benchmark is stored for MNE; upper bounds only." | |
| }, | |
| { | |
| "model": "Nova Mini 1.0", | |
| "repository": "ModernoTech/Nova-Mini", | |
| "hardware": "MacBook Air 2014", | |
| "hardware_id": "air-2014", | |
| "bandwidth_gbps": 25.6, | |
| "ram_gb": 4.0, | |
| "context_tokens": 8192, | |
| "context_label": "8K", | |
| "context_supported_or_validated": true, | |
| "max_position_documented": 40960, | |
| "artifact_size_bytes": 484220288, | |
| "artifact_status": "PUBLICADO", | |
| "weight_basis": "artifact size on Hugging Face", | |
| "active_payload_bytes_for_memory_bound": 354334802, | |
| "active_payload_basis": "active param count x 0.5 GiB/B x 1.10 (Q4 + 10% parsed overhead), ESTIMADO", | |
| "theoretical_tok_s_conventional_ram": 77.576, | |
| "ssd_mne_upper_tok_s": [ | |
| { | |
| "ssd_cache_miss": 0.1, | |
| "cache_label": "90%", | |
| "upper Tok_s": 60.606 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.05, | |
| "cache_label": "95%", | |
| "upper Tok_s": 121.212 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.01, | |
| "cache_label": "99%", | |
| "upper Tok_s": 606.061 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.005, | |
| "cache_label": "99.5%", | |
| "upper Tok_s": 1212.121 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.001, | |
| "cache_label": "99.9%", | |
| "upper Tok_s": 6060.606 | |
| } | |
| ], | |
| "kv_cache_bytes_est": 939524096, | |
| "kv_cache_status": "ESTIMADO", | |
| "conventional_resident_total_gb_est": 1.443153, | |
| "mne_resident_total_gb_est": 1.808438, | |
| "ssd_required_bytes": 484220288, | |
| "feasible_conventional": "VIABLE con margen de memoria (límite superior de presión, no medición)", | |
| "feasible_mne": "ESCENARIO VIRTUOSO DE RAM (cache capado; no prueba de throughput)", | |
| "throughput_status": "ESTIMADO (techo de ancho de banda, no benchmark)", | |
| "throughput_note": "No real benchmark is stored for MNE; upper bounds only." | |
| }, | |
| { | |
| "model": "Nova Mini 1.0", | |
| "repository": "ModernoTech/Nova-Mini", | |
| "hardware": "Lenovo Yoga 720", | |
| "hardware_id": "yoga-720", | |
| "bandwidth_gbps": 34.1, | |
| "ram_gb": 8.0, | |
| "context_tokens": 8192, | |
| "context_label": "8K", | |
| "context_supported_or_validated": true, | |
| "max_position_documented": 40960, | |
| "artifact_size_bytes": 484220288, | |
| "artifact_status": "PUBLICADO", | |
| "weight_basis": "artifact size on Hugging Face", | |
| "active_payload_bytes_for_memory_bound": 354334802, | |
| "active_payload_basis": "active param count x 0.5 GiB/B x 1.10 (Q4 + 10% parsed overhead), ESTIMADO", | |
| "theoretical_tok_s_conventional_ram": 103.333, | |
| "ssd_mne_upper_tok_s": [ | |
| { | |
| "ssd_cache_miss": 0.1, | |
| "cache_label": "90%", | |
| "upper Tok_s": 60.606 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.05, | |
| "cache_label": "95%", | |
| "upper Tok_s": 121.212 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.01, | |
| "cache_label": "99%", | |
| "upper Tok_s": 606.061 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.005, | |
| "cache_label": "99.5%", | |
| "upper Tok_s": 1212.121 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.001, | |
| "cache_label": "99.9%", | |
| "upper Tok_s": 6060.606 | |
| } | |
| ], | |
| "kv_cache_bytes_est": 939524096, | |
| "kv_cache_status": "ESTIMADO", | |
| "conventional_resident_total_gb_est": 1.443153, | |
| "mne_resident_total_gb_est": 1.808438, | |
| "ssd_required_bytes": 484220288, | |
| "feasible_conventional": "VIABLE con margen de memoria (límite superior de presión, no medición)", | |
| "feasible_mne": "ESCENARIO VIRTUOSO DE RAM (cache capado; no prueba de throughput)", | |
| "throughput_status": "ESTIMADO (techo de ancho de banda, no benchmark)", | |
| "throughput_note": "No real benchmark is stored for MNE; upper bounds only." | |
| }, | |
| { | |
| "model": "Nova Mini 1.0", | |
| "repository": "ModernoTech/Nova-Mini", | |
| "hardware": "MacBook Neo A18 Pro", | |
| "hardware_id": "neo", | |
| "bandwidth_gbps": 60.0, | |
| "ram_gb": 8.0, | |
| "context_tokens": 8192, | |
| "context_label": "8K", | |
| "context_supported_or_validated": true, | |
| "max_position_documented": 40960, | |
| "artifact_size_bytes": 484220288, | |
| "artifact_status": "PUBLICADO", | |
| "weight_basis": "artifact size on Hugging Face", | |
| "active_payload_bytes_for_memory_bound": 354334802, | |
| "active_payload_basis": "active param count x 0.5 GiB/B x 1.10 (Q4 + 10% parsed overhead), ESTIMADO", | |
| "theoretical_tok_s_conventional_ram": 181.818, | |
| "ssd_mne_upper_tok_s": [ | |
| { | |
| "ssd_cache_miss": 0.1, | |
| "cache_label": "90%", | |
| "upper Tok_s": 60.606 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.05, | |
| "cache_label": "95%", | |
| "upper Tok_s": 121.212 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.01, | |
| "cache_label": "99%", | |
| "upper Tok_s": 606.061 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.005, | |
| "cache_label": "99.5%", | |
| "upper Tok_s": 1212.121 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.001, | |
| "cache_label": "99.9%", | |
| "upper Tok_s": 6060.606 | |
| } | |
| ], | |
| "kv_cache_bytes_est": 939524096, | |
| "kv_cache_status": "ESTIMADO", | |
| "conventional_resident_total_gb_est": 1.443153, | |
| "mne_resident_total_gb_est": 1.808438, | |
| "ssd_required_bytes": 484220288, | |
| "feasible_conventional": "VIABLE con margen de memoria (límite superior de presión, no medición)", | |
| "feasible_mne": "ESCENARIO VIRTUOSO DE RAM (cache capado; no prueba de throughput)", | |
| "throughput_status": "ESTIMADO (techo de ancho de banda, no benchmark)", | |
| "throughput_note": "No real benchmark is stored for MNE; upper bounds only." | |
| }, | |
| { | |
| "model": "Nova Mini 1.0", | |
| "repository": "ModernoTech/Nova-Mini", | |
| "hardware": "MacBook Air M4", | |
| "hardware_id": "air-m4", | |
| "bandwidth_gbps": 120.0, | |
| "ram_gb": 16.0, | |
| "context_tokens": 8192, | |
| "context_label": "8K", | |
| "context_supported_or_validated": true, | |
| "max_position_documented": 40960, | |
| "artifact_size_bytes": 484220288, | |
| "artifact_status": "PUBLICADO", | |
| "weight_basis": "artifact size on Hugging Face", | |
| "active_payload_bytes_for_memory_bound": 354334802, | |
| "active_payload_basis": "active param count x 0.5 GiB/B x 1.10 (Q4 + 10% parsed overhead), ESTIMADO", | |
| "theoretical_tok_s_conventional_ram": 363.636, | |
| "ssd_mne_upper_tok_s": [ | |
| { | |
| "ssd_cache_miss": 0.1, | |
| "cache_label": "90%", | |
| "upper Tok_s": 60.606 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.05, | |
| "cache_label": "95%", | |
| "upper Tok_s": 121.212 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.01, | |
| "cache_label": "99%", | |
| "upper Tok_s": 606.061 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.005, | |
| "cache_label": "99.5%", | |
| "upper Tok_s": 1212.121 | |
| }, | |
| { | |
| "ssd_cache_miss": 0.001, | |
| "cache_label": "99.9%", | |
| "upper Tok_s": 6060.606 | |
| } | |
| ], | |
| "kv_cache_bytes_est": 939524096, | |
| "kv_cache_status": "ESTIMADO", | |
| "conventional_resident_total_gb_est": 1.443153, | |
| "mne_resident_total_gb_est": 1.808438, | |
| "ssd_required_bytes": 484220288, | |
| "feasible_conventional": "VIABLE con margen de memoria (límite superior de presión, no medición)", | |
| "feasible_mne": "ESCENARIO VIRTUOSO DE RAM (cache capado; no prueba de throughput)", | |
| "throughput_status": "ESTIMADO (techo de ancho de banda, no benchmark)", | |
| "throughput_note": "No real benchmark is stored for MNE; upper bounds only." | |
| } | |
| ], | |
| "charts": [ | |
| "tokens-per-second.png", | |
| "ram-vs-mne.png", | |
| "context-performance.png", | |
| "memory-breakdown.png", | |
| "model-size-vs-ram.png", | |
| "cache-hit-analysis.png", | |
| "prefill-vs-decode.png" | |
| ] | |
| } |