Yes, just — 2.0 GB spare
Llama 3.3 70B Instruct at Q4_K_M fits your 2× GeForce RTX 4090 entirely on the GPUs at 8K context, at an estimated 15 tokens per second. Past 14K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Still the creative-writing favourite: consistent voice, takes direction. Needs 48 GB to sit comfortably on GPU at Q4.
Hardware requirements What hardware do I need to run Llama 3.3 70B Instruct? →At Q4_K_M with an 8K context: a 64 GB GPU (Instinct MI210) or a 96 GB Mac (M2 Max). 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 |
|---|---|---|---|---|---|---|
| Q8_0 | 69.9 GB | 73.0 GB | — | ~1.2 | −0.1% ppl | 28.2 GB over |
| Q6_K | 53.9 GB | 57.0 GB | — | ~2.5 | −0.4% ppl | 12.2 GB over |
| Q5_K_M | 46.6 GB | 49.7 GB | — | ~4.9 | −0.8% ppl | 4.9 GB over |
| Q4_K_M | 39.7 GB | 42.8 GB | 14K | 15 | −1.9% ppl | Recommended |
| Q3_K_M | 32.1 GB | 35.2 GB | 38K | 19 | −5.4% ppl | Long context |
| Q2_K | 27.5 GB | 30.6 GB | 53K | 22 | −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-3.3-70B-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 2× GeForce RTX 4090
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Llama 4 Scout 109B-A17B 109B MoE · same family |
Q4_K_M · 63.4 GB | ~4.2 | CPU offload |
| Llama 3.1 8B Instruct 8.03B · same family |
Q4_K_M · 6.1 GB | 135 | Runs great |
| Llama 3.2 3B Instruct 3.21B · same family |
Q4_K_M · 3.3 GB | 338 | Runs great |
| Llama 3.2 1B Instruct 1.24B · same family |
Q4_K_M · 1.5 GB | 875 | Runs great |
| DeepSeek-R1-Distill-Llama 70B 70.6B · similar size |
Q4_K_M · 42.8 GB | 15 | Tight fit |
| gpt-oss 120B 117B MoE · similar size |
MXFP4 · 61.4 GB | ~17 | CPU offload |
| Mistral Small 4 119B-A6B 119B MoE · similar size |
Q4_K_M · 67.7 GB | ~10 | CPU offload |
Llama 3.3 70B Instruct on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
42.8 GB | ~1.0 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
42.8 GB | ~1.1 | CPU offload |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
42.8 GB | — | Won't fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
42.8 GB | ~1.7 | CPU offload |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
42.8 GB | ~1.7 | CPU offload |
| Instinct MI210 62.4 GB usable · 1638 GB/s |
42.8 GB | 25 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
42.8 GB | 5.6 | Tight fit |
| M2 Max · 96 GB 72.0 GB usable · 400 GB/s |
42.8 GB | 5.6 | Runs great |