NVIDIA · Ada
What runs on a RTX 4080 Super
16 GB at 736 GB/s. The largest model that fits at Q4_K_M is gpt-oss 20B-A3.6B, at roughly 145 tokens per second.
Runs comfortably
6.4 GB of 14.2 GB · 45%014 GB
Weights
4.6 GB
KV cache
1.0 GB
Runtime overhead
0.8 GB
Llama 3.1 8B at Q4_K_M leaves 7.8 GB spare on a RTX 4080 Super. There is room to raise the context length or move up a quantisation level.
Generation84.9tok/s
Prompt processing2720tok/s
Max context70Ktokens
KV per 1K tokens0GB
Every quantisation of Llama 3.1 8B on a RTX 4080 Super
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 15.0 GB | 16.8 GB | Won't fit | — | 9.58 |
| INT8 / W8A8 | 8.50 | 7.7 GB | 9.5 GB | Runs comfortably | 46K | 53.2 |
| Q8_0 (GGUF) | 8.50 | 7.7 GB | 9.5 GB | Runs comfortably | 46K | 53.2 |
| FP8 (E4M3) | 8.00 | 7.5 GB | 9.3 GB | Runs comfortably | 48K | 54.7 |
| Q6_K | 6.56 | 6.1 GB | 8.0 GB | Runs comfortably | 58K | 65.7 |
| AWQ 4-bit | 4.25 | 5.4 GB | 7.2 GB | Runs comfortably | 64K | 73.6 |
| GPTQ 4-bit | 4.25 | 5.4 GB | 7.2 GB | Runs comfortably | 64K | 73.6 |
| MXFP4 | 4.25 | 5.4 GB | 7.2 GB | Runs comfortably | 64K | 73.6 |
| Q5_K_M | 5.67 | 5.3 GB | 7.1 GB | Runs comfortably | 65K | 75.0 |
| Q5_K_S | 5.52 | 5.2 GB | 7.0 GB | Runs comfortably | 66K | 76.8 |
| Q4_K_M | 4.85 | 4.6 GB | 6.4 GB | Runs comfortably | 70K | 84.9 |
| Q4_K_S | 4.58 | 4.4 GB | 6.2 GB | Runs comfortably | 72K | 88.6 |
| Q4_0 | 4.55 | 4.4 GB | 6.2 GB | Runs comfortably | 72K | 89.1 |
| IQ4_XS | 4.25 | 4.1 GB | 5.9 GB | Runs comfortably | 74K | 93.7 |
| Q3_K_M | 3.91 | 3.8 GB | 5.7 GB | Runs comfortably | 77K | 99.5 |
| IQ3_M | 3.70 | 3.7 GB | 5.5 GB | Runs comfortably | 78K | 104 |
| IQ3_XXS | 3.06 | 3.2 GB | 5.0 GB | Runs comfortably | 82K | 118 |
| Q2_K | 2.63 | 2.8 GB | 4.6 GB | Runs comfortably | 85K | 130 |
| IQ2_XXS | 2.06 | 2.3 GB | 4.2 GB | Runs comfortably | 89K | 151 |
| IQ1_M | 1.75 | 2.1 GB | 3.9 GB | Runs comfortably | 91K | 165 |
Models on a RTX 4080 Super
Q4_K_M at 8K context. Bandwidth sets the speed; capacity sets the ceiling.
| Model | Params | Weights | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|
| DeepSeek-R1 671B-A37B | 671B | 379.0 GB | Won't fit | — | 1.85 |
| Qwen3 235B-A22B | 235.1B | 132.8 GB | Won't fit | — | 3.05 |
| gpt-oss 120B-A5.1B | 116.8B | 66.0 GB | Won't fit | — | 14.3 |
| Llama 4 Scout 109B-A17B | 109B | 61.7 GB | Won't fit | — | 4.43 |
| Qwen2.5 72B | 72.7B | 41.2 GB | Won't fit | — | 1.18 |
| Llama 3.1 70B | 70.5B | 40.0 GB | Won't fit | — | 1.22 |
| Mixtral 8x7B | 46.7B | 26.4 GB | Won't fit | — | 8.45 |
| Command R 35B | 35.0B | 20.1 GB | Won't fit | — | 1.77 |
| Yi-1.5 34B | 34.4B | 19.5 GB | Won't fit | — | 4.00 |
| Qwen3 32B | 32.8B | 18.6 GB | Won't fit | — | 4.39 |
| Qwen2.5-Coder 32B | 32.8B | 18.6 GB | Won't fit | — | 4.39 |
| DeepSeek-R1-Distill-Qwen 32B | 32.8B | 18.6 GB | Won't fit | — | 4.39 |
| Qwen3 30B-A3B | 30.5B | 17.3 GB | Won't fit | — | 40.9 |
| Gemma 3 27B | 27.4B | 15.6 GB | Won't fit | — | 7.98 |
| Mistral Small 24B | 23.6B | 13.4 GB | Won't fit | — | 15.3 |
| gpt-oss 20B-A3.6B | 20.9B | 11.9 GB | Fits, but tight | 33K | 145 |
| Qwen3 14B | 14.8B | 8.5 GB | Runs comfortably | 32K | 48.0 |
| Phi-4 14B | 14.7B | 8.4 GB | Runs comfortably | 16K | 47.6 |
| Mistral NeMo 12B | 12.3B | 7.0 GB | Runs comfortably | 41K | 57.0 |
| Gemma 3 12B | 12.2B | 7.0 GB | Runs comfortably | 98K | 57.7 |
| GLM-4 9B | 9.4B | 5.4 GB | Runs comfortably | 128K | 77.9 |
| Qwen3 8B | 8.2B | 4.7 GB | Runs comfortably | 62K | 82.1 |
| Llama 3.1 8B | 8.0B | 4.6 GB | Runs comfortably | 70K | 84.9 |
| DeepSeek-R1-Distill-Llama 8B | 8.0B | 4.6 GB | Runs comfortably | 70K | 84.9 |
| Qwen2.5 7B | 7.6B | 4.4 GB | Runs comfortably | 128K | 94.4 |
| Mistral 7B v0.3 | 7.3B | 4.1 GB | Runs comfortably | 32K | 93.9 |
| Gemma 3 4B | 4.3B | 2.5 GB | Runs comfortably | 128K | 159 |
| Qwen3 4B | 4.0B | 2.3 GB | Runs comfortably | 79K | 149 |
| Llama 3.2 3B | 3.2B | 1.8 GB | Runs comfortably | 106K | 188 |
| Llama 3.2 1B | 1.2B | 0.7 GB | Runs comfortably | 128K | 497 |