Model · Meta
Llama 3.2 3B
3B · Q4_K_M · 1.9 GB · open weights · curated for general · repo created 2024-09-18
On the radar
76
Heat Score · rising ▲ · 100% confidence
- Rank among scored models
- 5 of 45
- Trending score · Hugging Face
- 24
- Downloads, rolling 30 days · Hugging Face
- 1,605,242
- Downloads vs. the reading of 2026-09-05
- +11.8%
- Likes · Hugging Face
- 2,563
- API price per 1M tokens, in / out · OpenRouter
- $0.049999999999999996 / $0.33
Measured signals as of 2026-09-12 12:00 UTC · How the Heat Score is made →
Downloads, daily readingsdaily last · UTC
2026-08-31 · 1.1M2026-09-12 · 1.6M
Heat is a composite of measured signals only: each component is the model's percentile among models with a full week of history — trending level (35%), 7-day download growth (30%), 7-day trending change (15%), 30-day downloads (15%) and Hub likes (5%). Missing components renormalize the weights and lower the shown confidence; nothing is guessed. Trending and downloads come from the Hugging Face Hub — the download counter is a rolling 30-day window, not unique users — and input pricing from OpenRouter (CC BY 4.0). The full formula, thresholds and flag rules are on the methodology page.
What it needs
◇ Estimated— Estimated: computed from our curated model and hardware catalog — not a live reading.Weights, context cache and runtime overhead at four reference contexts. The total is the model's own; what differs per machine is the usable memory it has to fit into.
The attention shape of this model is unpublished, so the context cache cannot be estimated. Verdicts stay UNKNOWN rather than guessed.
All memory figures are estimates: measured quantized file size + computed context memory + runtime overhead, with a 12% safety margin on your hardware. Real usage varies with runtime version and settings.
Where it runs
◇ Estimated— Estimated: computed from our curated model and hardware catalog — not a live reading.Every tracked GPU and Mac at 8K and 32K context with a full-precision (f16) cache — the same engine as the finder and the GPU pages.
The attention shape of this model is unpublished, so the context cache cannot be estimated. Verdicts stay UNKNOWN rather than guessed.
| Device | 8K context | 32K context |
|---|---|---|
| RTX 407012 GB · 10.6 GB usable | Unknown | Unknown |
| RTX 3060 12GB12 GB · 10.6 GB usable | Unknown | Unknown |
| RTX 408016 GB · 14.1 GB usable | Unknown | Unknown |
| RTX 508016 GB · 14.1 GB usable | Unknown | Unknown |
| RTX 4060 Ti 16GB16 GB · 14.1 GB usable | Unknown | Unknown |
| RTX 5060 Ti 16GB16 GB · 14.1 GB usable | Unknown | Unknown |
| RTX 5070 Ti16 GB · 14.1 GB usable | Unknown | Unknown |
| RTX 309024 GB · 21.1 GB usable | Unknown | Unknown |
| RTX 409024 GB · 21.1 GB usable | Unknown | Unknown |
| RTX 509032 GB · 28.2 GB usable | Unknown | Unknown |
| Mac mini M4 Pro 64GB64 GB unified · 44.8 GB usable | Unknown | Unknown |
| Mac Studio M4 Max 64GB64 GB unified · 44.8 GB usable | Unknown | Unknown |
| Mac Studio M3 Ultra 96GB96 GB unified · 67.2 GB usable | Unknown | Unknown |
| NVIDIA DGX Spark128 GB unified · 112.6 GB usable | Unknown | Unknown |
GGUF is the quantized single-file format local runtimes load (Ollama, LM Studio, llama.cpp); our memory figures are measured from the linked GGUF file. The original repo holds full-precision safetensors — a much larger download meant for GPUs with far more memory.
Check it against your own machine →Or rent it
Rental fit cannot be estimated without the model's attention shape.
Terms on this page
More from Meta
- Llama 3.1 8BHeat 76
- Llama 3.3 70BHeat 53