FR
Catalogue · 26 models

How much VRAM for each LLM?

Memory needed in Q4, Q8 and FP16 with an 8k-token context, and the cheapest machine that runs it. Click a model for details by context and by card.

All26Llama3Qwen8OpenAI2Google2Mistral4Microsoft1DeepSeek3GLM2Kimi1
26 results
Dense · Qwen2025-04
Qwen3 4B4.0 B · dense
4 GBQ46 GBQ810 GBFP16

From: RTX 3060 12 GB · €1,180

Dense · Llama2024-07
Llama 3.1 8B8.0 B · dense
6 GBQ410 GBQ818 GBFP16

From: RTX 3060 12 GB · €1,180

Dense · Qwen2025-04
Qwen3 8B8.2 B · dense
7 GBQ411 GBQ819 GBFP16

From: RTX 3060 12 GB · €1,180

Dense · Google2025-03
Gemma 3 12B12 B · dense
10 GBQ415 GBQ827 GBFP16

From: RTX 3060 12 GB · €1,180

Dense · Mistral2024-07
Mistral Nemo 12B12 B · dense
9 GBQ415 GBQ827 GBFP16

From: RTX 3060 12 GB · €1,180

Dense · Microsoft2024-12
Phi-4 14B15 B · dense
11 GBQ418 GBQ833 GBFP16

From: RTX 3060 12 GB · €1,180

Dense · Qwen2025-04
Qwen3 14B15 B · dense
11 GBQ418 GBQ833 GBFP16

From: RTX 3060 12 GB · €1,180

MoE · OpenAI2025-08
gpt-oss-20b21 B · 3.6 B active
14 GBQ424 GBQ845 GBFP16

From: RTX 4060 Ti 16 GB · €1,350

Dense · Mistral2025-01
Mistral Small 24B24 B · dense
17 GBQ428 GBQ852 GBFP16

From: 2 × RTX 3060 12 GB · €1,460

Dense · Google2025-03
Gemma 3 27B27 B · dense
19 GBQ432 GBQ859 GBFP16

From: 2 × RTX 3060 12 GB · €1,460

Dense · Qwen2026
Qwen3.8 27B28 B · dense
20 GBQ433 GBQ861 GBFP16

From: 2 × RTX 3060 12 GB · €1,460

MoE · Qwen2025-04
Qwen3 30B-A3B31 B · 3.3 B active
20 GBQ435 GBQ865 GBFP16

From: 2 × RTX 3060 12 GB · €1,460

Dense · Qwen2025-04
Qwen3 32B33 B · dense
23 GBQ439 GBQ871 GBFP16

From: 2 × RTX 3060 12 GB · €1,460

Dense · Qwen2024-11
Qwen2.5 Coder 32B33 B · dense
23 GBQ439 GBQ871 GBFP16

From: 2 × RTX 3060 12 GB · €1,460

Dense · DeepSeek2025-01
DeepSeek R1 Distill 32B33 B · dense
23 GBQ439 GBQ871 GBFP16

From: 2 × RTX 3060 12 GB · €1,460

MoE · Mistral2023-12
Mixtral 8x7B47 B · 13 B active
31 GBQ453 GBQ899 GBFP16

From: 2 × RTX 4060 Ti 16 GB · €1,800

Dense · Llama2024-12
Llama 3.3 70B71 B · dense
47 GBQ481 GBQ8151 GBFP16

From: Mini-PC Ryzen AI Max+ 395 128 GB · €2,300

MoE · GLM2025-07
GLM-4.5-Air 106B106 B · 12 B active
69 GBQ4120 GBQ8224 GBFP16

From: Mini-PC Ryzen AI Max+ 395 128 GB · €2,300

MoE · OpenAI2025-08
gpt-oss-120b117 B · 5.1 B active
75 GBQ4131 GBQ8247 GBFP16

From: Mini-PC Ryzen AI Max+ 395 128 GB · €2,300

Dense · Mistral2024-11
Mistral Large 123B123 B · dense
81 GBQ4140 GBQ8261 GBFP16

From: Mini-PC Ryzen AI Max+ 395 128 GB · €2,300

MoE · Qwen2025-04
Qwen3 235B-A22B235 B · 22 B active
150 GBQ4263 GBQ8495 GBFP16

From: Mac Studio M3 Ultra 512 GB · €11,500

MoE · GLM2025-07
GLM-4.5 355B355 B · 32 B active
226 GBQ4398 GBQ8748 GBFP16

From: Mac Studio M3 Ultra 512 GB · €11,500

Dense · Llama2024-07
Llama 3.1 405B405 B · dense
259 GBQ4455 GBQ8855 GBFP16

From: Mac Studio M3 Ultra 512 GB · €11,500

MoE · DeepSeek2025-01
DeepSeek R1 671B671 B · 37 B active
424 GBQ4748 GBQ81,410 GBFP16

From: 6 × A100 80 GB · €72,000

MoE · DeepSeek2025-08
DeepSeek V3.1 671B671 B · 37 B active
424 GBQ4748 GBQ81,410 GBFP16

From: 6 × A100 80 GB · €72,000

MoE · Kimi2025-07
Kimi K2 1T1,000 B · 32 B active
631 GBQ41,114 GBQ82,101 GBFP16

From: 5 × H200 141 GB · €171,000