Ling-3.0 Flash hardware requirements
What is Ling-3.0 Flash?
Ling-3.0 Flash is the larger sibling of Ling-3.0 Tiny, released in August 2026 by inclusionAI, Ant Group's AGI initiative. This mixture-of-experts model activates 5.1B parameters per token and targets coding, agent workflows, reasoning and contexts up to 256k. Only a small share of its weights is used for each token, but all of them must fit in VRAM or system RAM. Thinking is on by default, and the license is MIT.
About the model
- Parameters
- 127.49B total · 5.1B active (MoE)
- Attention
- Hybrid attention (only some layers use full attention)
- Max context
- 262,144 tokens
- Released
- 2026-08-02
- Model card
- Ling-3.0 Flash on Hugging Face
Other sizes in this series
| Model | Parameters | Baseline quant | Memory needed (8k) | GeForce RTX 4060 | GeForce RTX 5060 Ti 16GB | GeForce RTX 3090 |
|---|---|---|---|---|---|---|
| Ling-3.0 Tiny | 7.89B total · 1.3B active (MoE) | Q4_K_M | 5.3 GB | Runs great | Runs great | Runs great |
| Ling-3.0 Flashthis model | 127.49B total · 5.1B active (MoE) | Q4_K_M | 75.4 GB | Won't run | Won't run | Won't run |
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q4_K_Mbaseline | 77.01 GB | Good balance | Official GGUF · inclusionAI |
| Q8_0 | 135.62 GB | Near-lossless | Official GGUF · inclusionAI |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| Q4_K_M | 75.4 | 75.4 | 75.6 | 75.9 | 76.5 | 77.7 | 80.1 |
| Q8_0 | 132.5 | 132.6 | 132.7 | 133.0 | 133.6 | 134.8 | 137.2 |
Which GPUs can run Ling-3.0 Flash?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Ultra · 256 GB | Runs great | est. 106.3 tok/s74.4–138.2theoretical estimate ±30% | Q4_K_M | 77.7 / 179.2 GB | Unified memory | up to 256k | — | — |
| Apple M5 Max (40-core GPU) · 128 GB | Runs great | est. 96.3 tok/s67.4–125.2theoretical estimate ±30% | Q4_K_M | 77.7 / 89.6 GB | Unified memory | up to 256k | — | — |
| Apple M4 Max (40-core GPU) · 128 GB | Runs great | est. 88.6 tok/s62.0–115.2theoretical estimate ±30% | Q4_K_M | 77.7 / 89.6 GB | Unified memory | up to 256k | — | — |
| Apple M3 Ultra · 256 GB | Runs great | est. 84.6 tok/s59.2–110.0theoretical estimate ±30% | Q4_K_M | 77.7 / 179.2 GB | Unified memory | up to 256k | — | — |
| Apple M2 Ultra · 128 GB | Runs great | est. 83.4 tok/s58.4–108.4theoretical estimate ±30% | Q4_K_M | 77.7 / 89.6 GB | Unified memory | up to 256k | — | — |
| NVIDIA DGX Spark · 128 GB | Runs great | est. 52.8 tok/s36.9–68.6theoretical estimate ±30% | Q4_K_M | 77.7 / 116.9 GB | Unified memory | up to 256k | — | $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 128 GB | Runs great | est. 48.4 tok/s33.9–62.9theoretical estimate ±30% | Q4_K_M | 77.7 / 89.6 GB | Unified memory | up to 256k | — | $1,999 launch MSRP (128 GB) |
| DDR5-6000 dual-channel CPU · 96 GB | Runs slowly | est. 13.1 tok/s9.2–17.0theoretical estimate ±30% | Q4_K_M | 77.1 GB RAM | CPU only | up to 256k |
| — |
| DDR5-5600 dual-channel CPU · 96 GB | Runs slowly | est. 12.2 tok/s8.5–15.9theoretical estimate ±30% | Q4_K_M | 77.1 GB RAM | CPU only | up to 256k |
| — |
| Apple M4 · 32 GB | Won't run | — | Q4_K_M | needs 77.7 GB | — | — |
| — |
| Apple M4 Max (32-core GPU) · 36 GB | Won't run | — | Q4_K_M | needs 77.7 GB | — | — |
| — |
| Apple M4 Pro · 64 GB | Won't run | — | Q4_K_M | needs 77.7 GB | — | — |
| — |
| Apple M5 · 32 GB | Won't run | — | Q4_K_M | needs 77.7 GB | — | — |
| — |
| Apple M5 Max (32-core GPU) · 36 GB | Won't run | — | Q4_K_M | needs 77.7 GB | — | — |
| — |
| Apple M5 Pro · 64 GB | Won't run | — | Q4_K_M | needs 77.7 GB | — | — |
| — |
| Apple M6 · 32 GB | Won't run | — | Q4_K_M | needs 77.7 GB | — | — |
| — |
| Intel Arc B580 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $290 street (as of 2026-08-09) |
| DDR4-3200 dual-channel CPU · 64 GB | Won't run | — | Q4_K_M | needs 77.1 GB | — | — |
| — |
| GeForce GTX 1080 Ti | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 2080 Ti | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 3050 8GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $249 launch MSRP |
| GeForce RTX 3060 12GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $250 street (as of 2026-08-09) |
| GeForce RTX 3070 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 3080 10GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 3080 12GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 3090 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $1,050 street (as of 2026-08-09) |
| GeForce RTX 3090 Ti | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $1,999 launch MSRP |
| GeForce RTX 4060 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $299 launch MSRP |
| GeForce RTX 4060 Laptop | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| — |
| GeForce RTX 4060 Ti 16GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $399 launch MSRP |
| GeForce RTX 4070 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Laptop | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| — |
| GeForce RTX 4070 Super | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Ti Super | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 4080 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $1,199 launch MSRP |
| GeForce RTX 4080 Laptop | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| — |
| GeForce RTX 4080 Super | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 4090 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $2,755 street (as of 2026-08-09) |
| GeForce RTX 4090 Laptop | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| — |
| GeForce RTX 5060 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $429 street (as of 2026-08-09) |
| GeForce RTX 5070 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $949 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| — |
| GeForce RTX 5080 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $1,256 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| — |
| GeForce RTX 5090 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $4,200 street (as of 2026-08-09) |
| GeForce RTX 5090 Laptop | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| — |
| Radeon RX 7800 XT | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $499 launch MSRP |
| Radeon RX 7900 XT | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $899 launch MSRP |
| Radeon RX 7900 XTX | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $999 launch MSRP |
| Radeon RX 9060 XT 16GB | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $449 street (as of 2026-08-09) |
| Radeon RX 9070 | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Won't run | — | Q4_K_M | needs 75.4 GB | — | — |
| $689 street (as of 2026-08-09) |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Cheapest GPUs that run it
No GPU with a current street price reaches Runs great or Runs well at Q4_K_M. The table above lists Macs, unified-memory PCs and CPU setups.
Measured results for Ling-3.0 Flash
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Ling-3.0 Flash need?
At Q4_K_M the file is 77.01 GB; with 8k context a graphics card needs about 75.4 GB (weights 74.79 GB, KV cache 0.1 GB, compute buffer 0.6 GB). Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM and does not use this model’s MTP (multi-token prediction) block yet, so it never loads it. A Mac counts the whole file, so it needs a little more.
What is the cheapest GPU that runs Ling-3.0 Flash well?
No GPU with a current street price reaches Runs great or Runs well at Q4_K_M. The best tracked option is Apple M5 Ultra · 256 GB: Runs great.
Can Ling-3.0 Flash run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Won't run; GeForce RTX 5060 Ti 16GB — Won't run; GeForce RTX 3090 — Won't run.
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.