Best LLM Models
/
Beste LLMs für den lokalen Einsatz
🤖
Agent
💬
Text
💻
Code
🌐
Open Source
🎨
Bild
🎬
Video
Teilen
Deutsch
English
简体中文
繁體中文
العربية
Français
Deutsch
Hell
Alle Modelle
OpenAI
Zhipu
DeepSeek
Google
Kimi
Alibaba
Weitere Modelle
Unknown
Meta
NVIDIA
IBM
Mistral
Ai2
Cohere
Microsoft
MiniMax
Xiaomi
Tencent
Thinky
Ant Group
#
Modell
Score
Votes
Preis
Kontext
15
glm-5.3-max
1485.6
10,559
$1.72
/
$5.41
1M
17
kimi-k3-max
1484.5
20,911
$3.762
/
$18.81
1049k
28
GLM-5.3 Flash (Z AI)
1475.0
9,479
$0.15
/
$0.5
1049k
37
glm-5.2-max
1472.3
36,471
$1.254
/
$5.016
1M
43
MiMo V2.5 Pro
1467.5
60,523
$0.435
/
$0.87
1049k
46
GLM-5.1
1465.4
48,503
$1.4
/
$4.4
200k
49
deepseek-v4-pro-high-20260813
1462.1
8,623
$0.435
/
$0.87
1049k
51
Kimi K2.6 (Moonshot AI)
1460.5
37,497
$0.95
/
$4
262k
55
GLM-5
1457.6
27,600
$1
/
$3.2
205k
56
DeepSeek V4 Pro
1457.5
54,142
$0.435
/
$0.87
1M
59
Tencent Hy3
1455.9
8,023
$0.066
/
$0.26
262k
65
deepseek-v4-pro-high-preview
1454.9
51,494
$0.435
/
$0.87
1049k
68
Kimi K2.5 Thinking
1450.3
70,513
$0.3
/
$1.9
256k
81
Qwen3.5 397B-A17B
1442.1
76,643
$0.6
/
$3.6
262k
82
MiniMax M3
1441.8
48,130
$0.3
/
$1.2
512k
83
GLM-4.7
1441.7
11,892
$0.6
/
$2.2
205k
84
Inkling
1439.2
25,509
$1.0888
/
$4.40964
1049k
87
Gemma 4 26B-A4B
1438.0
5,804
$0.05
/
$0.29
262k
88
Qwen3.8 27B
1437.8
10,256
$0.5
/
$3
1M
91
DeepSeek V4 Flash
1435.6
48,890
$0.098
/
$0.196
1M
95
MiMo-V2.5
1433.5
44,446
$0.4
/
$2
1049k
99
Kimi K2.5
1431.0
7,990
$0.5
/
$2.7
262k
103
muse-glimmer
1427.0
3,665
—
—
105
mistral-medium-3.5
1426.5
10,998
$1.5
/
$7.5
256k
108
NVIDIA Nemotron 3 Ultra
1425.6
10,691
$0.625
/
$3.125
256k
110
DeepSeek V3.2
1425.2
46,464
$0.2174
/
$0.326
128k
111
GLM-4.6
1424.8
35,065
$0.6
/
$2.2
205k
113
Qwen3 235B A22B Instruct 2507
1423.1
95,656
$1.026
/
$3.078
262k
116
DeepSeek R1 0528
1421.4
18,089
$0.7
/
$2.5
164k
120
Kimi K2 0711
1417.8
27,027
$0.57
/
$2.3
131k
122
DeepSeek-V3.1
1417.3
14,604
$0.19
/
$0.71
131k
123
Qwen3.5 122B A10B
1416.9
28,349
$0.437
/
$3.496
131k
124
DeepSeek V3.1 Thinking
1416.0
11,462
$0.2
/
$0.7
128k
126
MiniMax M2.7
1414.7
68,700
$0.315
/
$1.26
205k
130
Qwen3 VL 235B A22B Instruct
1413.9
11,219
$0.4
/
$1.6
131k
133
hunyuan-hy3-preview
1412.5
6,606
—
—
135
GLM-4.5
1411.3
23,707
$0.6
/
$2.2
131k
139
Qwen3.5 27B
1407.9
27,228
$0.27
/
$2.16
260k
141
Inkling Small
1404.3
18,408
$0.5
/
$1.2
1M
143
Qwen 3 235b A22B
1402.5
37,381
$0.3
/
$0.5
262k
149
Qwen3 Next 80B A3B Instruct
1399.4
22,527
$0.15
/
$1.2
131k
150
DeepSeek-R1
1398.0
18,524
$1.35
/
$5.4
128k
152
DeepSeek V3 0324
1395.8
44,781
$0.27
/
$1.12
164k
153
Qwen3 VL 235B A22B Thinking
1395.2
7,780
$0.5
/
$6
33k
155
Qwen3.5 35B A3B
1395.1
29,033
$0.225
/
$1.8
260k
158
mimo-v2-flash (non-thinking)
1392.0
46,110
$0.1
/
$0.3
256k
161
MiniMax-M2.5
1390.3
40,852
$0.3
/
$1.2
205k
168
mimo-v2-flash (thinking)
1386.0
10,742
$0.1
/
$0.3
256k
169
MiniMax-M2.1
1383.9
16,623
$0.27
/
$1.1
205k
174
Trinity Large Preview
1378.5
29,739
$0
/
$0
131k
175
GLM-4.6V (Z AI)
1378.4
2,761
$0.3
/
$0.9
128k
181
GLM-4.5-Air
1373.2
30,367
$0.2
/
$1.1
131k
183
Trinity Large Thinking
1369.0
28,956
$0.25
/
$0.8
262k
184
Qwen3 Next 80B A3B Thinking
1368.9
13,379
$0.15
/
$1.2
131k
185
GLM 4.7 Flash
1366.2
11,495
$0.07
/
$0.4
200k
186
Gemma 3 27B
1365.2
46,418
$0.119
/
$0.2
98k
191
Nemotron 3 Super 120B A12B
1360.6
7,458
$0.3
/
$2.4
262k
193
DeepSeek V3
1358.4
21,770
$0.58
/
$1.68
164k
195
Mistral Small 3.2 (Mistral AI)
1356.7
17,390
$0.1
/
$0.3
128k
196
intellect-3
1356.3
5,278
—
—
197
Command A 03-2025
1353.6
55,441
$2.5
/
$10
256k
199
GLM-4.5V (Z AI)
1352.6
4,816
$0.6
/
$1.8
128k
200
Nemotron 3.5 Lightning
1352.5
7,900
$0.1
/
$0.25
262k
201
GPT OSS 120B
1352.3
29,948
$0.35
/
$0.75
128k
207
Llama 3.1 Nemotron Ultra 253B
1347.5
2,549
$0
/
$0
128k
215
nvidia-llama-3.3-nemotron-super-49b-v1.5
1343.2
3,313
—
—
218
Gemma 3 12B
1341.7
3,829
$0.05
/
$0.1
131k
219
granite-4.2-30b
1341.6
3,261
—
—
224
QwQ 32B
1335.8
25,087
$0.287
/
$0.861
131k
228
Llama 3.1 405B Instruct
1335.1
41,375
$1.95
/
$1.95
128k
230
Llama 3.1 405B Instruct
1333.2
59,656
$1.95
/
$1.95
128k
231
olmo-3.1-32b-instruct
1330.0
11,454
—
—
233
Nvidia Nemotron Super 49B
1327.8
2,218
$0.15
/
$0.15
128k
234
molmo-2-8b
1327.6
792
—
—
236
Llama 4 Maverick 17b 128e Instruct
1326.8
39,355
$0
/
$0
128k
241
deepseek-v2.5-1210
1323.3
6,795
—
—
244
Llama 4 Scout 17B 16E Instruct
1321.4
29,735
$0.2
/
$0.78
128k
245
ring-flash-2.0
1320.9
6,898
—
—
250
Llama 3.3 70b Instruct
1317.6
54,410
$0
/
$0
128k
251
GPT OSS 20B
1317.2
10,393
$0.2
/
$0.3
128k
252
Gemma 3n E4b It
1317.2
22,079
$0
/
$0
128k
254
Nemotron 3 Nano 30B A3B
1314.3
15,326
$0.05
/
$0.2
262k
256
athene-v2-chat
1314.1
24,739
—
—
263
deepseek-v2.5
1307.1
24,572
—
—
264
olmo-3-32b-think
1306.7
5,683
—
—
265
athene-70b-0725
1306.4
19,621
—
—
266
Granite 4.1 8B
1305.9
4,018
$0.05
/
$0.1
131k
267
Mistral Large 2.1
1305.4
28,073
$2
/
$6
131k
269
Gemma 3 4B IT
1303.1
4,171
$0.05
/
$0.1
131k
270
Mistral Small 3.1 24B
1303.1
32,614
$0.106
/
$0.318
131k
271
Qwen2.5 72B
1302.8
39,406
$0.357
/
$0.408
131k
272
Llama 3.1 Nemotron 70B Instruct
1298.7
7,140
$0
/
$0
128k
273
granite-4.2-3b
1294.1
3,081
—
—
275
Llama 3.1 70b Instruct
1293.1
55,240
$0
/
$0
128k
277
jamba-1.5-large
1289.2
8,662
—
—
281
Granite 4.2 8B
1287.1
3,098
$0.1
/
$0.15
131k
283
llama-3.1-nemotron-51b-instruct
1286.3
3,749
—
—
284
llama-3.1-tulu-3-70b
1285.9
2,846
—
—
285
ibm-granite-h-small
1285.6
5,531
—
—
286
olmo-3.1-32b-think
1285.5
8,114
—
—
288
gemma-2-9b-it-simpo
1280.1
10,072
—
—
289
nemotron-4-340b-instruct
1276.8
19,659
—
—
290
Llama 3 70B Instruct
1276.2
156,876
$0.51
/
$0.74
8k
291
Cohere: Command R+
1276.0
9,866
$2.856
/
$14.246
128k
293
Mistral Small 24B
1274.2
14,681
$0.1155
/
$0.3465
33k
297
Aya Expanse 32B
1267.0
27,124
—
128k
299
deepseek-coder-v2
1265.0
15,147
—
—
300
qwen2-72b-instruct
1261.5
37,325
—
—
301
command-r-plus
1261.4
77,554
—
—
306
olmo-2-0325-32b-instruct
1251.4
3,334
—
—
307
Command R
1250.1
10,140
$0.15
/
$0.6
128k
310
jamba-1.5-mini
1239.5
8,858
—
—
311
Ministral 8B (latest)
1237.4
4,781
$0.1
/
$0.1
128k
313
qwen1.5-110b-chat
1233.8
26,195
—
—
315
qwen1.5-72b-chat
1233.1
39,302
—
—
317
Mixtral 8x22B
1229.2
51,416
$2
/
$6
66k
318
Command R
1226.5
54,036
$0.15
/
$0.6
128k
321
Llama 3 8B Instruct
1223.3
104,642
$0.04
/
$0.04
8k
323
Aya Expanse 8B
1222.8
9,818
—
8k
325
llama-3.1-tulu-3-8b
1220.3
2,896
—
—
326
zephyr-orpo-141b-A35b-v0.1
1212.6
4,652
—
—
327
yi-1.5-34b-chat
1212.6
24,146
—
—
328
Llama 3.1 8B Instruct
1211.1
49,605
$0
/
$0
16k
329
granite-3.1-8b-instruct
1208.2
3,090
—
—
331
qwen1.5-32b-chat
1203.6
21,741
—
—
332
Gemma 2 2b It
1199.9
46,616
$0
/
$0
128k
333
phi-3-medium-4k-instruct
1197.5
25,055
—
—
334
Mixtral 8x7B Instruct v0.1
1196.8
73,503
$0.488
/
$0.758
32k
335
dbrx-instruct-preview
1195.1
32,191
—
—
336
qwen1.5-14b-chat
1190.7
17,839
—
—
337
internlm2_5-20b-chat
1190.5
9,901
—
—
338
deepseek-llm-67b-chat
1184.5
4,932
—
—
339
wizardlm-70b
1184.4
8,214
—
—
340
yi-34b-chat
1183.4
15,483
—
—
341
granite-3.0-8b-instruct
1182.7
6,638
—
—
342
openchat-3.5
1182.6
7,968
—
—
343
openchat-3.5-0106
1182.3
12,637
—
—
344
gemma-1.1-7b-it
1182.2
23,893
—
—
345
snowflake-arctic-instruct
1179.6
32,832
—
—
346
granite-3.1-2b-instruct
1178.6
3,188
—
—
347
tulu-2-dpo-70b
1177.3
6,535
—
—
348
openhermes-2.5-mistral-7b
1175.5
5,006
—
—
349
vicuna-33b
1172.5
22,479
—
—
350
starling-lm-7b-beta
1170.7
16,056
—
—
351
phi-3-small-8k-instruct
1170.7
17,766
—
—
352
llama-2-70b-chat
1170.3
38,492
—
—
353
starling-lm-7b-alpha
1167.1
10,224
—
—
354
Llama 3.2 3B Instruct
1166.4
7,936
$0
/
$0
33k
355
nous-hermes-2-mixtral-8x7b-dpo
1164.1
3,777
—
—
356
granite-3.0-2b-instruct
1156.2
6,837
—
—
357
llama2-70b-steerlm-chat
1154.3
3,585
—
—
358
QwQ 32B
1154.1
3,231
$0.4
/
$0.4
33k
359
solar-10.7b-instruct-v1.0
1152.0
4,155
—
—
360
dolphin-2.2.1-mistral-7b
1151.9
1,679
—
—
361
mpt-30b-chat
1150.3
2,572
—
—
362
wizardlm-13b
1149.1
7,044
—
—
364
falcon-180b-chat
1147.6
1,295
—
—
365
qwen1.5-7b-chat
1143.5
4,737
—
—
366
phi-3-mini-4k-instruct-june-2024
1142.8
12,297
—
—
367
vicuna-13b
1141.1
19,367
—
—
368
llama-2-13b-chat
1141.1
19,174
—
—
369
qwen-14b-chat
1138.9
4,964
—
—
371
gemma-7b-it
1137.3
8,925
—
—
372
codellama-34b-instruct
1136.5
7,366
—
—
373
zephyr-7b-beta
1130.4
11,118
—
—
374
phi-3-mini-128k-instruct
1129.4
20,685
—
—
375
phi-3-mini-4k-instruct
1127.8
20,118
—
—
376
guanaco-33b
1127.1
2,921
—
—
377
zephyr-7b-alpha
1126.5
1,785
—
—
378
stripedhyena-nous-7b
1121.2
5,182
—
—
379
codellama-70b-instruct
1118.8
1,143
—
—
380
gemma-1.1-2b-it
1116.2
10,854
—
—
381
vicuna-7b
1114.9
6,923
—
—
382
smollm2-1.7b-instruct
1114.3
2,199
—
—
383
Llama 3.2 1b Instruct
1110.8
8,045
$0
/
$0
128k
384
mistral-7b-instruct
1109.9
8,977
—
—
385
llama-2-7b-chat
1107.6
14,148
—
—
386
gemma-2b-it
1093.2
4,780
—
—
387
qwen1.5-4b-chat
1090.6
7,597
—
—
388
olmo-7b-instruct
1073.3
6,328
—
—
389
koala-13b
1070.5
6,965
—
—
390
alpaca-13b
1069.6
5,745
—
—
391
gpt4all-13b-snoozy
1067.1
1,743
—
—
392
mpt-7b-chat
1062.9
3,924
—
—
393
chatglm3-6b
1056.1
4,658
—
—
394
RWKV-4-Raven-14B
1041.9
4,845
—
—
395
chatglm2-6b
1024.3
2,658
—
—
396
oasst-pythia-12b
1023.0
6,310
—
—
397
chatglm-6b
995.4
4,914
—
—
398
fastchat-t5-3b
992.1
4,203
—
—
399
dolly-v2-12b
981.9
3,412
—
—
400
llama-13b
974.5
2,391
—
—
401
stablelm-tuned-alpha-7b
952.8
3,287
—
—
Best LLM Models