Yes — with 39.7 GB to spare
Ling 3.0 Tiny 7.9B-A1.3B at Q4_K_M fits your 2× GeForce RTX 3090 entirely on the GPUs at 8K context, at an estimated 298 tokens per second. There is room for its full 128K window.
An 8B MoE with 1.3B active and a latent KV cache on only 6 of 24 layers — reasoning and tool use sized for Apple Silicon and edge boxes.
Hardware requirements What hardware do I need to run Ling 3.0 Tiny 7.9B-A1.3B? →At Q4_K_M with an 8K context: a 8 GB GPU (RTX 4060 Laptop) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 14.7 GB | 15.4 GB | 128K | 90 | Reference | Long context |
| Q8_0 | 7.8 GB | 8.5 GB | 128K | 169 | −0.1% ppl | Long context |
| Q6_K | 6.0 GB | 6.7 GB | 128K | 220 | −0.4% ppl | Long context |
| Q5_K_M | 5.2 GB | 5.9 GB | 128K | 254 | −0.8% ppl | Long context |
| Q4_K_M | 4.4 GB | 5.1 GB | 128K | 298 | −1.9% ppl | Recommended |
| Q3_K_M | 3.6 GB | 4.2 GB | 128K | 368 | −5.4% ppl | Long context |
| Q2_K | 3.1 GB | 3.7 GB | 128K | 430 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 6 of its 24 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.
How to run it
$ llama-server \
-hf inclusionAI/Ling-3.0-tiny:Q4_K_M \
-c 8192 -ngl 99
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a 2× GeForce RTX 3090
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Ling 3.0 Flash 124B-A5B 124B MoE · same family |
Q4_K_M · 70.4 GB | ~12 | CPU offload |
| Gemma 4 E4B 8.0B · similar size |
Q4_K_M · 5.2 GB | 126 | Runs great |
| Llama 3.1 8B Instruct 8.03B · similar size |
Q4_K_M · 6.1 GB | 125 | Runs great |
| Qwen3 8B 8.19B · similar size |
Q4_K_M · 6.3 GB | 123 | Runs great |
| DeepSeek-R1-Distill-Qwen 7B 7.62B · similar size |
Q4_K_M · 5.3 GB | 132 | Runs great |
| Qwen2.5-Coder 7B 7.62B · similar size |
Q4_K_M · 5.3 GB | 132 | Runs great |
| Fara 7B 8.29B · similar size |
Q4_K_M · 5.7 GB | 122 | Runs great |
Ling 3.0 Tiny 7.9B-A1.3B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
5.1 GB | 82 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
5.1 GB | 115 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
5.1 GB | 43 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
5.1 GB | 321 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
5.1 GB | 306 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
5.1 GB | 143 | Runs great |