Only with CPU offload
Ling 3.0 Flash 124B-A5B at Q4_K_M needs 70.4 GB but only 46.4 GB is addressable, so about 34% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 13 tokens per second — usable for batch work, painful for chat.
A 124B hybrid (5 linear-attention layers per MLA layer) with 5.1B active: SWE-bench Pro 56.6 and AIME 93 claimed. Built for 96–128 GB machines.
Hardware requirements What hardware do I need to run Ling 3.0 Flash 124B-A5B? →At Q4_K_M with an 8K context: a 141 GB GPU (H200 SXM) or a 128 GB Mac. Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
Fits instead: Ling 3.0 Tiny 7.9B-A1.3B (5.1 GB)
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 122.7 GB | 123.4 GB | — | ~4.2 | −0.1% ppl | 77.0 GB over |
| Q6_K | 94.7 GB | 95.4 GB | — | ~6.5 | −0.4% ppl | 49.0 GB over |
| Q5_K_M | 81.8 GB | 82.5 GB | — | ~8.6 | −0.8% ppl | 36.1 GB over |
| Q4_K_M | 69.7 GB | 70.4 GB | — | ~13 | −1.9% ppl | 24.0 GB over |
| Q3_K_M | 56.4 GB | 57.1 GB | — | ~24 | −5.4% ppl | 10.7 GB over |
| Q2_K | 48.4 GB | 49.0 GB | — | ~59 | −15% ppl | 2.6 GB over |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 7 of its 42 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-flash:Q4_K_M \
-c 8192 -ngl 27
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a Radeon Pro W7900
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE · same family |
Q4_K_M · 5.1 GB | 275 | Runs great |
| Nemotron 3 Super 120B-A12B 124B MoE · similar size |
Q4_K_M · 70.4 GB | ~5.3 | CPU offload |
| Qwen3.5 122B-A10B 125B MoE · similar size |
Q4_K_M · 71.1 GB | ~6.3 | CPU offload |
| Mistral Small 4 119B-A6B 119B MoE · similar size |
Q4_K_M · 67.7 GB | ~10 | CPU offload |
| gpt-oss 120B 117B MoE · similar size |
MXFP4 · 61.4 GB | ~18 | CPU offload |
| Llama 4 Scout 109B-A17B 109B MoE · similar size |
Q4_K_M · 63.4 GB | ~4.5 | CPU offload |
| Qwen3.8-Flash-Next 180B-A6B 180B MoE · similar size |
Q4_K_M · 102.0 GB | — | Won't fit |
Ling 3.0 Flash 124B-A5B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
70.4 GB | — | Won't fit |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
70.4 GB | — | Won't fit |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
70.4 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
70.4 GB | ~6.9 | CPU offload |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
70.4 GB | ~6.9 | CPU offload |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
70.4 GB | — | Won't fit |
| DGX Spark · 128 GB 96.0 GB usable · 273 GB/s |
70.4 GB | 25 | Runs great |
| H200 SXM 139.4 GB usable · 4800 GB/s |
70.4 GB | 390 | Runs great |