Model · InclusionAI
Ling 3.0 Flash
127B MoE · Q4_K_M · 70.1 GB · open weights · curated for general, agents · repo created 2026-08-02
On the radar
30
Heat Score · falling ▼ · 100% confidence
- Rank among scored models
- 39 of 45
- Trending score · Hugging Face
- 11
- Downloads, rolling 30 days · Hugging Face
- 17,264
- Downloads vs. the reading of 2026-09-05
- -11.6%
- Likes · Hugging Face
- 405
- API price per 1M tokens, in / out · OpenRouter
- $0.020999999999999998 / $0.063
Measured signals as of 2026-09-12 12:00 UTC · How the Heat Score is made →
Downloads, daily readingsdaily last · UTC
2026-08-30 · 20K2026-09-12 · 17K
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.
| Context | Weights | Context cache | Overhead | Total |
|---|---|---|---|---|
| 8K | 70.1 | 0.4 | 3.0 | 73.4 GB |
| 32K | 70.1 | 1.5 | 3.7 | 75.3 GB |
| 64K | 70.1 | 3.0 | 4.7 | 77.8 GB |
| 128K | 70.1 | 5.9 | 6.7 | 82.7 GB |
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.
Runs comfortably (EXCELLENT or GOOD) on 1 of 14 tracked devices at 8K context.
| Device | 8K context | 32K context |
|---|---|---|
| RTX 407012 GB · 10.6 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| RTX 3060 12GB12 GB · 10.6 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| RTX 408016 GB · 14.1 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| RTX 508016 GB · 14.1 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| RTX 4060 Ti 16GB16 GB · 14.1 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| RTX 5060 Ti 16GB16 GB · 14.1 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| RTX 5070 Ti16 GB · 14.1 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| RTX 309024 GB · 21.1 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| RTX 409024 GB · 21.1 GB usable | Offload required73.4 GB | Offload required75.3 GB |
| RTX 509032 GB · 28.2 GB usable | Offload required73.4 GB | Offload required75.3 GB |
| Mac mini M4 Pro 64GB64 GB unified · 44.8 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| Mac Studio M4 Max 64GB64 GB unified · 44.8 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| Mac Studio M3 Ultra 96GB96 GB unified · 67.2 GB usable | Not recommended73.4 GB | Not recommended75.3 GB |
| NVIDIA DGX Spark128 GB unified · 112.6 GB usable | Excellent fit73.4 GB | Excellent fit75.3 GB |
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
Cheapest measured rental class that runs it comfortably (EXCELLENT or GOOD at 8K): H200 at $3.98/h, the median across verified on-demand offers.
2026-09-12 12:00 UTC
Terms on this page
More from InclusionAI
- Ling 3.0 TinyHeat 66