Local LLM memory planner

Will it fit, and how fast?

Pick a model and a GPU. You get the full memory breakdown — weights, KV cache and runtime overhead — the longest context that still fits, and the tokens per second to expect.

Runs comfortably

6.4 GB of 21.8 GB · 30%
022 GB
Weights 4.6 GB
KV cache 1.0 GB
Runtime overhead 0.8 GB

Llama 3.1 8B at Q4_K_M leaves 15.3 GB spare on a RTX 4090. There is room to raise the context length or move up a quantisation level.

Generation116tok/s
Prompt processing4315tok/s
Max context128Ktokens
KV per 1K tokens0GB

Every quantisation of Llama 3.1 8B on a RTX 4090

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 15.0 GB 16.8 GB Runs comfortably 48K 38.8
INT8 / W8A8 8.50 7.7 GB 9.5 GB Runs comfortably 106K 72.6
Q8_0 (GGUF) 8.50 7.7 GB 9.5 GB Runs comfortably 106K 72.6
FP8 (E4M3) 8.00 7.5 GB 9.3 GB Runs comfortably 108K 74.7
Q6_K 6.56 6.1 GB 8.0 GB Runs comfortably 118K 89.6
AWQ 4-bit 4.25 5.4 GB 7.2 GB Runs comfortably 124K 100
GPTQ 4-bit 4.25 5.4 GB 7.2 GB Runs comfortably 124K 100
MXFP4 4.25 5.4 GB 7.2 GB Runs comfortably 124K 100
Q5_K_M 5.67 5.3 GB 7.1 GB Runs comfortably 125K 102
Q5_K_S 5.52 5.2 GB 7.0 GB Runs comfortably 126K 105
Q4_K_M 4.85 4.6 GB 6.4 GB Runs comfortably 128K 116
Q4_K_S 4.58 4.4 GB 6.2 GB Runs comfortably 128K 121
Q4_0 4.55 4.4 GB 6.2 GB Runs comfortably 128K 121
IQ4_XS 4.25 4.1 GB 5.9 GB Runs comfortably 128K 127
Q3_K_M 3.91 3.8 GB 5.7 GB Runs comfortably 128K 135
IQ3_M 3.70 3.7 GB 5.5 GB Runs comfortably 128K 141
IQ3_XXS 3.06 3.2 GB 5.0 GB Runs comfortably 128K 160
Q2_K 2.63 2.8 GB 4.6 GB Runs comfortably 128K 176
IQ2_XXS 2.06 2.3 GB 4.2 GB Runs comfortably 128K 204
IQ1_M 1.75 2.1 GB 3.9 GB Runs comfortably 128K 223

Popular hardware

RTX 5090
32 GB · 1792 GB/sRTX 4090
24 GB · 1008 GB/sRTX 3090
24 GB · 936 GB/sRTX 5080
16 GB · 960 GB/sRTX 5070 Ti
16 GB · 896 GB/sRTX 5070
12 GB · 672 GB/sRTX 4070 Ti Super
16 GB · 672 GB/sRTX 4070 Super
12 GB · 504 GB/sRTX 4070
12 GB · 504 GB/sRTX 4060 Ti 16GB
16 GB · 288 GB/sRTX 3080 10GB
10 GB · 760 GB/sRTX 3060 12GB
12 GB · 360 GB/s

Popular models

Llama 3.1 8B
8.0B · 32 layersLlama 3.1 70B
70.5B · 80 layersLlama 3.2 3B
3.2B · 28 layersLlama 3.2 1B
1.2B · 16 layersLlama 4 Scout 109B-A17B
109B · 48 layersQwen3 8B
8.2B · 36 layersQwen3 14B
14.8B · 40 layersQwen3 32B
32.8B · 64 layersQwen3 4B
4.0B · 36 layersQwen3 30B-A3B
30.5B · 48 layersQwen3 235B-A22B
235.1B · 94 layersQwen2.5-Coder 32B
32.8B · 64 layers