Yes, just — 0.9 GB spare
Llama 3.1 8B Instruct at Q4_K_M fits your GeForce RTX 3060 8 GB entirely on the GPU at 8K context, at an estimated 32 tokens per second. Past 15K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Still the most widely deployed local model, with the largest fine-tune ecosystem. Not the strongest 8B any more.
Hardware requirements What hardware do I need to run Llama 3.1 8B Instruct? →At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) 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 | 15.0 GB | 16.6 GB | — | ~3.3 | Reference | 9.6 GB over |
| Q8_0 | 7.9 GB | 9.5 GB | — | ~9.3 | −0.1% ppl | 2.5 GB over |
| Q6_K | 6.1 GB | 7.7 GB | 2K | ~17 | −0.4% ppl | 0.7 GB over |
| Q5_K_M | 5.3 GB | 6.9 GB | 8K | 27 | −0.8% ppl | Fits |
| Q4_K_M | 4.5 GB | 6.1 GB | 15K | 32 | −1.9% ppl | Recommended |
| Q3_K_M | 3.7 GB | 5.3 GB | 21K | 40 | −5.4% ppl | Long context |
| Q2_K | 3.1 GB | 4.7 GB | 26K | 46 | −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.
How to run it
$ llama-server \
-hf meta-llama/Llama-3.1-8B-Instruct: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 GeForce RTX 3060 8 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Llama 3.2 3B Instruct 3.21B · same family |
Q4_K_M · 3.3 GB | 80 | Runs great |
| Llama 3.2 1B Instruct 1.24B · same family |
Q4_K_M · 1.5 GB | 208 | Runs great |
| Llama 3.3 70B Instruct 70.6B · same family |
Q4_K_M · 42.8 GB | ~1.0 | CPU offload |
| Llama 4 Scout 109B-A17B 109B MoE · same family |
Q4_K_M · 63.4 GB | ~1.6 | CPU offload |
| Gemma 4 E4B 8.0B · similar size |
Q4_K_M · 5.2 GB | 32 | Runs great |
| Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE · similar size |
Q4_K_M · 5.1 GB | 76 | Runs great |
| Qwen3 8B 8.19B · similar size |
Q4_K_M · 6.3 GB | 32 | Tight fit |
Llama 3.1 8B Instruct on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
6.1 GB | 34 | Tight fit |
| Arc B570 8.8 GB usable · 380 GB/s |
6.1 GB | 51 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
6.1 GB | 48 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
6.1 GB | 15 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
6.1 GB | 135 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
6.1 GB | 129 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
6.1 GB | 50 | Runs great |