Tokenstead - Find the right AI model for your hardware

4 nodes / 512GB aggregate no link set

114 models / sorted by best_quality

Quality Fastest Least mem Newest

Model Fit Speed Memory Scores / Run

Runs comfortably

GLM-5.3-Flash UD-IQ1_S Unsloth

93.1GB 1000k ctx

Runs comfortably

29 tok/s

ⓘ estimated

93 / 512GB

93 / 92 / 91

FIT Runs comfortably

SPEED 29 tok/s

ⓘ estimated

MEMORY 93/512GB

GLM-5.3-Flash UD-Q2_K_XL Unsloth

109.0GB 1000k ctx

Runs comfortably

24 tok/s

ⓘ estimated

109 / 512GB

93 / 92 / 91

FIT Runs comfortably

SPEED 24 tok/s

ⓘ estimated

MEMORY 109/512GB

GLM-5.3-Flash UD-IQ3_XXS Unsloth

120.0GB 1000k ctx

Runs comfortably

22 tok/s

ⓘ estimated

120 / 512GB

93 / 92 / 91

FIT Runs comfortably

SPEED 22 tok/s

ⓘ estimated

MEMORY 120/512GB

GLM-5.3-Flash UD-Q4_K_XL Unsloth

200.0GB 1000k ctx

Runs comfortably

no data

200 / 512GB

93 / 92 / 91

FIT Runs comfortably

MEMORY 200/512GB

DeepSeek V4.1 Flash NVFP4

260.0GB 1000k ctx

Runs comfortably

no data

260 / 512GB

93 / 92 / 90

FIT Runs comfortably

MEMORY 260/512GB

DeepSeek V4 Flash 0731 UD-Q8_K_XL Unsloth

162.0GB 1000k ctx

Runs comfortably

no data

162 / 512GB

93 / 91 / 90

FIT Runs comfortably

MEMORY 162/512GB

DeepSeek V4 Flash 0731 UD-Q4_K_XL Unsloth

155.0GB 1000k ctx

Runs comfortably

no data

155 / 512GB

93 / 91 / 90

FIT Runs comfortably

MEMORY 155/512GB

Ornith-1.5-397B Q4_K_M

244.0GB 262k ctx

Runs comfortably

no data

244 / 512GB

93 / 91 / 89

FIT Runs comfortably

MEMORY 244/512GB

Ornith-1.5-397B Q5_K_M

286.0GB 262k ctx

Runs comfortably

no data

286 / 512GB

93 / 91 / 89

FIT Runs comfortably

MEMORY 286/512GB

Ornith-1.5-397B Q8_0

429.0GB 262k ctx

Runs comfortably

no data

429 / 512GB

93 / 91 / 89

FIT Runs comfortably

MEMORY 429/512GB

Ornith-1.5-397B Q6_K

331.0GB 262k ctx

Runs comfortably

no data

331 / 512GB

93 / 91 / 89

FIT Runs comfortably

MEMORY 331/512GB

Qwen3.8-Flash-Next EXL3_2BPW

62.7GB 262k ctx

Runs comfortably

39 tok/s

ⓘ estimated

63 / 512GB

92 / 92 / 89

FIT Runs comfortably

SPEED 39 tok/s

ⓘ estimated

MEMORY 63/512GB

Qwen3.8-Flash-Next EXL3_3BPW

85.0GB 262k ctx

Runs comfortably

33 tok/s

ⓘ estimated

85 / 512GB

92 / 92 / 89

FIT Runs comfortably

SPEED 33 tok/s

ⓘ estimated

MEMORY 85/512GB

Qwen3.8-Flash-Next UD-IQ1_S Unsloth

72.5GB 262k ctx

Runs comfortably

62 tok/s

ⓘ estimated

73 / 512GB

92 / 92 / 89

FIT Runs comfortably

SPEED 62 tok/s

ⓘ estimated

MEMORY 73/512GB

GLM 5.2 Q2_K Unsloth

240.0GB 1000k ctx

Runs comfortably

no data

240 / 512GB

91 / 92 / 88

FIT Runs comfortably

MEMORY 240/512GB

GLM 5.2 Q3_K_M Unsloth

365.0GB 1000k ctx

Runs comfortably

no data

365 / 512GB

91 / 92 / 88

FIT Runs comfortably

MEMORY 365/512GB

GLM 5.2 Q4_K_M Unsloth

410.0GB 1000k ctx

Runs comfortably

no data

410 / 512GB

91 / 92 / 88

FIT Runs comfortably

MEMORY 410/512GB

DeepSeek V3 0324 Q2_K

188.0GB 128k ctx

Runs comfortably

no data

188 / 512GB

92 / 88 / 87

FIT Runs comfortably

MEMORY 188/512GB

DeepSeek V3 0324 Q4_K_M

368.0GB 128k ctx

Runs comfortably

no data

368 / 512GB

92 / 88 / 87

FIT Runs comfortably

MEMORY 368/512GB

Ornith-1.5-35B-A3B Q8_0

37.8GB 262k ctx

Runs comfortably

48 tok/s

ⓘ estimated

38 / 512GB

91 / 89 / 86

FIT Runs comfortably

SPEED 48 tok/s

ⓘ estimated

MEMORY 38/512GB

Ornith-1.5-35B-A3B BF16

71.1GB 262k ctx

Runs comfortably

25 tok/s

ⓘ estimated

71 / 512GB

91 / 89 / 86

FIT Runs comfortably

SPEED 25 tok/s

ⓘ estimated

MEMORY 71/512GB

Ornith-1.5-35B-A3B Q6_K

29.2GB 262k ctx

Runs comfortably

62 tok/s

ⓘ estimated

29 / 512GB

91 / 89 / 86

FIT Runs comfortably

SPEED 62 tok/s

ⓘ estimated

MEMORY 29/512GB

Ornith-1.5-35B-A3B Q4_K_M

21.7GB 262k ctx

Runs comfortably

83 tok/s

ⓘ estimated

22 / 512GB

91 / 89 / 86

FIT Runs comfortably

SPEED 83 tok/s

ⓘ estimated

MEMORY 22/512GB

Ornith-1.5-35B-A3B Q5_K_M

25.3GB 262k ctx

Runs comfortably

71 tok/s

ⓘ estimated

25 / 512GB

91 / 89 / 86

FIT Runs comfortably

SPEED 71 tok/s

ⓘ estimated

MEMORY 25/512GB

Qwen3.6 35B A3B Q4_K_M

20.0GB 262k ctx

Runs comfortably

87 tok/s

ⓘ estimated

20 / 512GB

90 / 91 / 87

FIT Runs comfortably

SPEED 87 tok/s

ⓘ estimated

MEMORY 20/512GB

Qwen3.6 35B A3B Q8_0

37.0GB 262k ctx

Runs comfortably

47 tok/s

ⓘ estimated

37 / 512GB

90 / 91 / 87

FIT Runs comfortably

SPEED 47 tok/s

ⓘ estimated

MEMORY 37/512GB

Pokee-Isaac 28B FP16

56.0GB 10000k ctx

Runs comfortably

3 tok/s

ⓘ estimated

56 / 512GB

90 / 88 / 88

FIT Runs comfortably

SPEED 3 tok/s

ⓘ estimated

MEMORY 56/512GB

Pokee-Isaac 28B Q8_0

28.0GB 10000k ctx

Runs comfortably

5 tok/s

ⓘ estimated

28 / 512GB

90 / 88 / 88

FIT Runs comfortably

SPEED 5 tok/s

ⓘ estimated

MEMORY 28/512GB

Pokee-Isaac 28B Q4_K_M

16.0GB 10000k ctx

Runs comfortably

9 tok/s

ⓘ estimated

16 / 512GB

90 / 88 / 88

FIT Runs comfortably

SPEED 9 tok/s

ⓘ estimated

MEMORY 16/512GB

Qwen3 235B A22B Q4_K_M

125.0GB 128k ctx

Runs comfortably

13 tok/s

ⓘ estimated

125 / 512GB

88 / 90 / 85

FIT Runs comfortably

SPEED 13 tok/s

ⓘ estimated

MEMORY 125/512GB

Qwen3 235B A22B Q2_K

68.0GB 128k ctx

Runs comfortably

24 tok/s

ⓘ estimated

68 / 512GB

88 / 90 / 85

FIT Runs comfortably

SPEED 24 tok/s

ⓘ estimated

MEMORY 68/512GB

Qwen3.8-27B UD-IQ1_S Unsloth

6.2GB 262k ctx

Runs comfortably

24 tok/s

ⓘ estimated

6 / 512GB

88 / 89 / 85

FIT Runs comfortably

SPEED 24 tok/s

ⓘ estimated

MEMORY 6/512GB

Qwen3.8-27B UD-Q2_K_XL Unsloth

9.8GB 262k ctx

Runs comfortably

15 tok/s

ⓘ estimated

10 / 512GB

88 / 89 / 85

FIT Runs comfortably

SPEED 15 tok/s

ⓘ estimated

MEMORY 10/512GB

Qwen3.8-27B UD-Q4_K_XL Unsloth

17.6GB 262k ctx

Runs comfortably

9 tok/s

ⓘ estimated

18 / 512GB

88 / 89 / 85

FIT Runs comfortably

SPEED 9 tok/s

ⓘ estimated

MEMORY 18/512GB

Qwen3.8-27B NVFP4 Unsloth

15.2GB 262k ctx

Runs comfortably

10 tok/s

ⓘ estimated

15 / 512GB

88 / 89 / 85

FIT Runs comfortably

SPEED 10 tok/s

ⓘ estimated

MEMORY 15/512GB

Gemma 4 31B Q4_K_M

18.3GB 256k ctx

Runs comfortably

8 tok/s

ⓘ estimated

18 / 512GB

86 / 89 / 85

FIT Runs comfortably

SPEED 8 tok/s

ⓘ estimated

MEMORY 18/512GB

Gemma 4 31B Q8_0

32.6GB 256k ctx

Runs comfortably

5 tok/s

ⓘ estimated

33 / 512GB

86 / 89 / 85

FIT Runs comfortably

SPEED 5 tok/s

ⓘ estimated

MEMORY 33/512GB

Gemma 4 31B QAT

18.0GB 256k ctx

Runs comfortably

8 tok/s

ⓘ estimated

18 / 512GB

86 / 89 / 85

FIT Runs comfortably

SPEED 8 tok/s

ⓘ estimated

MEMORY 18/512GB

Gemma 4 31B BF16

61.4GB 256k ctx

Runs comfortably

2 tok/s

ⓘ estimated

61 / 512GB

86 / 89 / 85

FIT Runs comfortably

SPEED 2 tok/s

ⓘ estimated

MEMORY 61/512GB

Gemma 4 31B NVFP4

16.0GB 256k ctx

Runs comfortably

9 tok/s

ⓘ estimated

16 / 512GB

86 / 89 / 85

FIT Runs comfortably

SPEED 9 tok/s

ⓘ estimated

MEMORY 16/512GB

Gemma 4 26B A4B Q4_K_M

13.0GB 256k ctx

Runs comfortably

76 tok/s

ⓘ estimated

13 / 512GB

85 / 88 / 84

FIT Runs comfortably

SPEED 76 tok/s

ⓘ estimated

MEMORY 13/512GB

Gemma 4 26B A4B Q8_0

25.0GB 256k ctx

Runs comfortably

40 tok/s

ⓘ estimated

25 / 512GB

85 / 88 / 84

FIT Runs comfortably

SPEED 40 tok/s

ⓘ estimated

MEMORY 25/512GB

Gemma 4 26B A4B BF16

50.0GB 256k ctx

Runs comfortably

20 tok/s

ⓘ estimated

50 / 512GB

85 / 88 / 84

FIT Runs comfortably

SPEED 20 tok/s

ⓘ estimated

MEMORY 50/512GB

Gemma 4 26B A4B NVFP4

14.0GB 256k ctx

Runs comfortably

71 tok/s

ⓘ estimated

14 / 512GB

85 / 88 / 84

FIT Runs comfortably

SPEED 71 tok/s

ⓘ estimated

MEMORY 14/512GB

Qwen3.6 27B Q4_K_M

16.5GB 128k ctx

Runs comfortably

9 tok/s

ⓘ estimated

17 / 512GB

85 / 87 / 82

FIT Runs comfortably

SPEED 9 tok/s

ⓘ estimated

MEMORY 17/512GB

Qwen3.6 27B Q8_0

28.0GB 128k ctx

Runs comfortably

5 tok/s

ⓘ estimated

28 / 512GB

85 / 87 / 82

FIT Runs comfortably

SPEED 5 tok/s

ⓘ estimated

MEMORY 28/512GB

Qwen3 32B Q8_0

34.0GB 128k ctx

Runs comfortably

4 tok/s

ⓘ estimated

34 / 512GB

80 / 82 / 78

FIT Runs comfortably

SPEED 4 tok/s

ⓘ estimated

MEMORY 34/512GB

Qwen3 32B Q4_K_M

20.0GB 128k ctx

Runs comfortably

8 tok/s

ⓘ estimated

20 / 512GB

80 / 82 / 78

FIT Runs comfortably

SPEED 8 tok/s

ⓘ estimated

MEMORY 20/512GB

Qwen3 32B Q6_K

28.5GB 128k ctx

Runs comfortably

5 tok/s

ⓘ estimated

29 / 512GB

80 / 82 / 78

FIT Runs comfortably

SPEED 5 tok/s

ⓘ estimated

MEMORY 29/512GB

Qwen3 32B Q5_K_M

24.5GB 128k ctx

Runs comfortably

6 tok/s

ⓘ estimated

25 / 512GB

80 / 82 / 78

FIT Runs comfortably

SPEED 6 tok/s

ⓘ estimated

MEMORY 25/512GB

MiMo-V2.6-Flash Q2_K

77.0GB 108k cap

Runs comfortably

7 tok/s

ⓘ estimated

77 / 512GB

78 / 77 / 76

FIT Runs comfortably

SPEED 7 tok/s

ⓘ estimated

MEMORY 77/512GB

MiMo-V2.6-Flash FP8

177.7GB 83k cap

Runs comfortably

no data

178 / 512GB

78 / 77 / 76

FIT Runs comfortably

MEMORY 178/512GB

Ornith-1.5-9B Q8_0

9.8GB 262k ctx

Runs comfortably

15 tok/s

ⓘ estimated

10 / 512GB

78 / 76 / 74

FIT Runs comfortably

SPEED 15 tok/s

ⓘ estimated

MEMORY 10/512GB

Ornith-1.5-9B BF16

18.4GB 262k ctx

Runs comfortably

8 tok/s

ⓘ estimated

18 / 512GB

78 / 76 / 74

FIT Runs comfortably

SPEED 8 tok/s

ⓘ estimated

MEMORY 18/512GB

Ornith-1.5-9B Q6_K

7.6GB 262k ctx

Runs comfortably

20 tok/s

ⓘ estimated

8 / 512GB

78 / 76 / 74

FIT Runs comfortably

SPEED 20 tok/s

ⓘ estimated

MEMORY 8/512GB

Ornith-1.5-9B Q5_K_M

6.6GB 262k ctx

Runs comfortably

23 tok/s

ⓘ estimated

7 / 512GB

78 / 76 / 74

FIT Runs comfortably

SPEED 23 tok/s

ⓘ estimated

MEMORY 7/512GB

Ornith-1.5-9B Q4_K_M

5.8GB 262k ctx

Runs comfortably

26 tok/s

ⓘ estimated

6 / 512GB

78 / 76 / 74

FIT Runs comfortably

SPEED 26 tok/s

ⓘ estimated

MEMORY 6/512GB

Nemotron 3.5 Lightning Q4_K_M

32.0GB 1000k ctx

Runs comfortably

41 tok/s

ⓘ estimated

32 / 512GB

78 / 76 / 74

FIT Runs comfortably

SPEED 41 tok/s

ⓘ estimated

MEMORY 32/512GB

Nemotron 3.5 Lightning Q8_0

58.0GB 1000k ctx

Runs comfortably

23 tok/s

ⓘ estimated

58 / 512GB

78 / 76 / 74

FIT Runs comfortably

SPEED 23 tok/s

ⓘ estimated

MEMORY 58/512GB

Nemotron 3.5 Lightning FP16

60.0GB 1000k ctx

Runs comfortably

22 tok/s

ⓘ estimated

60 / 512GB

78 / 76 / 74

FIT Runs comfortably

SPEED 22 tok/s

ⓘ estimated

MEMORY 60/512GB

Qwen3 30B A3B Q4_K_M

15.5GB 128k ctx

Runs comfortably

98 tok/s

ⓘ estimated

16 / 512GB

75 / 78 / 72

FIT Runs comfortably

SPEED 98 tok/s

ⓘ estimated

MEMORY 16/512GB

Qwen3 30B A3B Q8_0

31.0GB 128k ctx

Runs comfortably

49 tok/s

ⓘ estimated

31 / 512GB

75 / 78 / 72

FIT Runs comfortably

SPEED 49 tok/s

ⓘ estimated

MEMORY 31/512GB

Phi-4 14B FP16

29.0GB 16k ctx

Runs comfortably

5 tok/s

ⓘ estimated

29 / 512GB

75 / 78 / 70

FIT Runs comfortably

SPEED 5 tok/s

ⓘ estimated

MEMORY 29/512GB

Phi-4 14B Q8_0

15.0GB 16k ctx

Runs comfortably

10 tok/s

ⓘ estimated

15 / 512GB

75 / 78 / 70

FIT Runs comfortably

SPEED 10 tok/s

ⓘ estimated

MEMORY 15/512GB

Phi-4 14B Q4_K_M

8.5GB 16k ctx

Runs comfortably

18 tok/s

ⓘ estimated

9 / 512GB

75 / 78 / 70

FIT Runs comfortably

SPEED 18 tok/s

ⓘ estimated

MEMORY 9/512GB

Xing4.0-29B-A4B BF16

62.4GB 256k ctx

Runs comfortably

11 tok/s

ⓘ estimated

62 / 512GB

75 / 73 / 72

FIT Runs comfortably

SPEED 11 tok/s

ⓘ estimated

MEMORY 62/512GB

Xing4.0-29B-A4B Q4_K_M

20.1GB 256k ctx

Runs comfortably

20 tok/s

ⓘ estimated

20 / 512GB

75 / 73 / 72

FIT Runs comfortably

SPEED 20 tok/s

ⓘ estimated

MEMORY 20/512GB

Llama 3.3 70B Instruct Q3_K_M

30.0GB 128k ctx

Runs comfortably

5 tok/s

ⓘ estimated

30 / 512GB

72 / 77 / 80

FIT Runs comfortably

SPEED 5 tok/s

ⓘ estimated

MEMORY 30/512GB

Llama 3.3 70B Instruct Q8_0

74.0GB 128k ctx

Runs comfortably

2 tok/s

ⓘ estimated

74 / 512GB

72 / 77 / 80

FIT Runs comfortably

SPEED 2 tok/s

ⓘ estimated

MEMORY 74/512GB

Llama 3.3 70B Instruct Q4_K_M

42.0GB 128k ctx

Runs comfortably

4 tok/s

ⓘ estimated

42 / 512GB

72 / 77 / 80

FIT Runs comfortably

SPEED 4 tok/s

ⓘ estimated

MEMORY 42/512GB

Llama 3.3 70B Instruct Q2_K

21.5GB 128k ctx

Runs comfortably

7 tok/s

ⓘ estimated

22 / 512GB

72 / 77 / 80

FIT Runs comfortably

SPEED 7 tok/s

ⓘ estimated

MEMORY 22/512GB

Qwen3 14B Q4_K_M

9.0GB 128k ctx

Runs comfortably

17 tok/s

ⓘ estimated

9 / 512GB

72 / 75 / 70

FIT Runs comfortably

SPEED 17 tok/s

ⓘ estimated

MEMORY 9/512GB

Qwen3 14B Q8_0

15.0GB 128k ctx

Runs comfortably

10 tok/s

ⓘ estimated

15 / 512GB

72 / 75 / 70

FIT Runs comfortably

SPEED 10 tok/s

ⓘ estimated

MEMORY 15/512GB

Gemma 4 12B Q8_0

13.0GB 128k ctx

Runs comfortably

12 tok/s

ⓘ estimated

13 / 512GB

70 / 74 / 72

FIT Runs comfortably

SPEED 12 tok/s

ⓘ estimated

MEMORY 13/512GB

Gemma 4 12B Q4_K_M

7.2GB 128k ctx

Runs comfortably

21 tok/s

ⓘ estimated

7 / 512GB

70 / 74 / 72

FIT Runs comfortably

SPEED 21 tok/s

ⓘ estimated

MEMORY 7/512GB

Gemma 3 27B Q8_0

28.0GB 128k ctx

Runs comfortably

5 tok/s

ⓘ estimated

28 / 512GB

68 / 71 / 72

FIT Runs comfortably

SPEED 5 tok/s

ⓘ estimated

MEMORY 28/512GB

Gemma 3 27B Q4_K_M

17.0GB 128k ctx

Runs comfortably

9 tok/s

ⓘ estimated

17 / 512GB

68 / 71 / 72

FIT Runs comfortably

SPEED 9 tok/s

ⓘ estimated

MEMORY 17/512GB

Qwen3 8B Q8_0

8.5GB 128k ctx

Runs comfortably

18 tok/s

ⓘ estimated

9 / 512GB

67 / 70 / 65

FIT Runs comfortably

SPEED 18 tok/s

ⓘ estimated

MEMORY 9/512GB

Qwen3 8B Q4_K_M

5.2GB 128k ctx

Runs comfortably

29 tok/s

ⓘ estimated

5 / 512GB

67 / 70 / 65

FIT Runs comfortably

SPEED 29 tok/s

ⓘ estimated

MEMORY 5/512GB

Gemma 3 12B Q4_K_M

7.5GB 128k ctx

Runs comfortably

20 tok/s

ⓘ estimated

8 / 512GB

62 / 65 / 68

FIT Runs comfortably

SPEED 20 tok/s

ⓘ estimated

MEMORY 8/512GB

Gemma 3 12B Q8_0

13.5GB 128k ctx

Runs comfortably

11 tok/s

ⓘ estimated

14 / 512GB

62 / 65 / 68

FIT Runs comfortably

SPEED 11 tok/s

ⓘ estimated

MEMORY 14/512GB

Mixtral 8x7B Instruct Q3_K_M

19.0GB 32k ctx

Runs comfortably

29 tok/s

ⓘ estimated

19 / 512GB

62 / 65 / 68

FIT Runs comfortably

SPEED 29 tok/s

ⓘ estimated

MEMORY 19/512GB

Mixtral 8x7B Instruct Q4_K_M

26.5GB 32k ctx

Runs comfortably

21 tok/s

ⓘ estimated

27 / 512GB

62 / 65 / 68

FIT Runs comfortably

SPEED 21 tok/s

ⓘ estimated

MEMORY 27/512GB

Kolibri 1 BF16

156.2GB 1048k ctx

Runs comfortably

no data

156 / 512GB

62 / 68 / 54

FIT Runs comfortably

MEMORY 156/512GB

Mistral Nemo 12B Q8_0

13.2GB 128k ctx

Runs comfortably

11 tok/s

ⓘ estimated

13 / 512GB

58 / 60 / 62

FIT Runs comfortably

SPEED 11 tok/s

ⓘ estimated

MEMORY 13/512GB

Mistral Nemo 12B Q4_K_M

7.3GB 128k ctx

Runs comfortably

21 tok/s

ⓘ estimated

7 / 512GB

58 / 60 / 62

FIT Runs comfortably

SPEED 21 tok/s

ⓘ estimated

MEMORY 7/512GB

Qwen3 4B Q4_K_M

2.6GB 32k ctx

Runs comfortably

58 tok/s

ⓘ estimated

3 / 512GB

58 / 60 / 56

FIT Runs comfortably

SPEED 58 tok/s

ⓘ estimated

MEMORY 3/512GB

Phi-4 Mini Q8_0

4.1GB 128k ctx

Runs comfortably

37 tok/s

ⓘ estimated

4 / 512GB

55 / 58 / 52

FIT Runs comfortably

SPEED 37 tok/s

ⓘ estimated

MEMORY 4/512GB

Phi-4 Mini Q4_K_M

2.5GB 128k ctx

Runs comfortably

60 tok/s

ⓘ estimated

3 / 512GB

55 / 58 / 52

FIT Runs comfortably

SPEED 60 tok/s

ⓘ estimated

MEMORY 3/512GB

Llama 3.1 8B Instruct FP16

16.0GB 128k ctx

Runs comfortably

9 tok/s

ⓘ estimated

16 / 512GB

52 / 55 / 62

FIT Runs comfortably

SPEED 9 tok/s

ⓘ estimated

MEMORY 16/512GB

Llama 3.1 8B Instruct Q8_0

8.0GB 128k ctx

Runs comfortably

19 tok/s

ⓘ estimated

8 / 512GB

52 / 55 / 62

FIT Runs comfortably

SPEED 19 tok/s

ⓘ estimated

MEMORY 8/512GB

Llama 3.1 8B Instruct Q4_K_M

4.5GB 128k ctx

Runs comfortably

33 tok/s

ⓘ estimated

5 / 512GB

52 / 55 / 62

FIT Runs comfortably

SPEED 33 tok/s

ⓘ estimated

MEMORY 5/512GB

Gemma 3 4B Q8_0

5.0GB 128k ctx

Runs comfortably

30 tok/s

ⓘ estimated

5 / 512GB

42 / 45 / 55

FIT Runs comfortably

SPEED 30 tok/s

ⓘ estimated

MEMORY 5/512GB

Gemma 3 4B Q4_K_M

3.0GB 128k ctx

Runs comfortably

50 tok/s

ⓘ estimated

3 / 512GB

42 / 45 / 55

FIT Runs comfortably

SPEED 50 tok/s

ⓘ estimated

MEMORY 3/512GB

Llama 3.2 3B Instruct Q8_0

3.5GB 128k ctx

Runs comfortably

43 tok/s

ⓘ estimated

4 / 512GB

35 / 38 / 50

FIT Runs comfortably

SPEED 43 tok/s

ⓘ estimated

MEMORY 4/512GB

Llama 3.2 3B Instruct Q4_K_M

2.0GB 128k ctx

Runs comfortably

75 tok/s

ⓘ estimated

2 / 512GB

35 / 38 / 50

FIT Runs comfortably

SPEED 75 tok/s

ⓘ estimated

MEMORY 2/512GB

Mellum2.1 12B Thinking Q4_K_M

7.0GB 131k ctx

Runs comfortably

90 tok/s

ⓘ estimated

7 / 512GB

FIT Runs comfortably

SPEED 90 tok/s

ⓘ estimated

MEMORY 7/512GB

Mellum2.1 12B Thinking FP16

24.3GB 131k ctx

Runs comfortably

29 tok/s

ⓘ estimated

24 / 512GB

FIT Runs comfortably

SPEED 29 tok/s

ⓘ estimated

MEMORY 24/512GB

Muse Glimmer 30B FP16

60.0GB 128k ctx

Runs comfortably

2 tok/s

ⓘ estimated

60 / 512GB

FIT Runs comfortably

SPEED 2 tok/s

ⓘ estimated

MEMORY 60/512GB

Muse Glimmer 30B Q8_0

33.0GB 128k ctx

Runs comfortably

4 tok/s

ⓘ estimated

33 / 512GB

FIT Runs comfortably

SPEED 4 tok/s

ⓘ estimated

MEMORY 33/512GB

Muse Glimmer 30B Q4_K_M

18.0GB 128k ctx

Runs comfortably

7 tok/s

ⓘ estimated

18 / 512GB

FIT Runs comfortably

SPEED 7 tok/s

ⓘ estimated

MEMORY 18/512GB

Muse Spark Open 816B-A42B NVFP4

484.0GB 1024k ctx

Runs comfortably

no data

484 / 512GB

FIT Runs comfortably

MEMORY 484/512GB

Muse Spark Open 816B-A42B UD-Q2_K_XL

311.0GB 1024k ctx

Runs comfortably

no data

311 / 512GB

FIT Runs comfortably

MEMORY 311/512GB

Muse Spark Open 816B-A42B UD-IQ1_S

176.0GB 1024k ctx

Runs comfortably

no data

176 / 512GB

FIT Runs comfortably

MEMORY 176/512GB

MiniMax M2.7 UD-IQ1_M Unsloth

60.7GB 200k ctx

Runs comfortably

2 tok/s

ⓘ estimated

61 / 512GB

FIT Runs comfortably

SPEED 2 tok/s

ⓘ estimated

MEMORY 61/512GB

MiniMax M2.7 UD-Q4_K_XL Unsloth

140.8GB 200k ctx

Runs comfortably

no data

141 / 512GB

FIT Runs comfortably

MEMORY 141/512GB

MiniMax M2.7 UD-Q2_K_XL Unsloth

75.3GB 200k ctx

Runs comfortably

2 tok/s

ⓘ estimated

75 / 512GB

FIT Runs comfortably

SPEED 2 tok/s

ⓘ estimated

MEMORY 75/512GB

MiniMax M3 MXFP4

256.5GB 1048k ctx

Runs comfortably

no data

257 / 512GB

FIT Runs comfortably

MEMORY 257/512GB

MiniMax M3 UD-Q4_K_XL Unsloth

264.9GB 1048k ctx

Runs comfortably

no data

265 / 512GB

FIT Runs comfortably

MEMORY 265/512GB

MiniMax M3 UD-IQ1_M Unsloth

128.4GB 1048k ctx

Runs comfortably

no data

128 / 512GB

FIT Runs comfortably

MEMORY 128/512GB

MiniMax M3 UD-Q2_K_XL Unsloth

143.0GB 1048k ctx

Runs comfortably

no data

143 / 512GB

FIT Runs comfortably

MEMORY 143/512GB

LFM2.5-24B-A2B FP8

24.0GB 131k ctx

Runs comfortably

65 tok/s

ⓘ estimated

24 / 512GB

FIT Runs comfortably

SPEED 65 tok/s

ⓘ estimated

MEMORY 24/512GB

LFM2.5-24B-A2B Q4_K_M

13.7GB 131k ctx

Runs comfortably

103 tok/s

ⓘ estimated

14 / 512GB

FIT Runs comfortably

SPEED 103 tok/s

ⓘ estimated

MEMORY 14/512GB

Runs tight

GLM 5.2 Q5_K_M Unsloth

510.0GB 409k cap

Runs tight

no data

510 / 512GB

91 / 92 / 88

FIT Runs tight

MEMORY 510/512GB

Run GLM-5.3-Flash in the cloud

No hardware? Host it - per-token API or flat subscription

OpenInference per-token

$0.13

/MONTH

DeepInfra per-token

$0.18

/MONTH

StreamLake per-token

$0.18

/MONTH

Decart per-token

$0.2

/MONTH

Sail Research per-token

$0.2

/MONTH

Novita per-token

$0.2

/MONTH

GMICloud per-token

$0.22

/MONTH

Relace per-token

$0.27

/MONTH

Near AI per-token

$0.28

/MONTH

InferenceNet per-token

$0.29

/MONTH

Phala per-token

$0.31

/MONTH

DigitalOcean per-token

$0.32

/MONTH

Wafer per-token

$0.32

/MONTH

Morph per-token

$0.34

/MONTH

Makora per-token

$0.34

/MONTH

AtlasCloud per-token

$0.36

/MONTH

CoreWeave per-token

$0.36

/MONTH

Friendli per-token

$0.36

/MONTH

Venice per-token

$0.36

/MONTH

Z.AI per-token

$0.36

/MONTH

Modal per-token

Serverless GPU inference platform. Serves open-weight models including reason...

$0.36

/MONTH

Crusoe per-token

$0.36

/MONTH

BaseTen per-token

$0.36

/MONTH

Together per-token

$0.36

/MONTH

SiliconFlow per-token

$0.36

/MONTH

Z.ai per-token

Official API and platform for Zhipu AI's open-source GLM models. GLM-5.2 avai...

pricing may be outdated

$0.36

/MONTH

Inceptron per-token

$0.37

/MONTH

Parasail per-token

$0.45

/MONTH

Fireworks per-token

$0.54

/MONTH

NextBit per-token

$0.55

/MONTH

Reka per-token

$0.65

/MONTH

OpenCode Go Go ($5 first month) subscription

Low-cost subscription for open coding models. $5 first month, then $10/month....

$10.0

/MONTH

Z.ai Coding Plan Lite subscription

Official API and platform for Zhipu AI's open-source GLM models. GLM-5.2 avai...

$10.0

/MONTH

Z.ai Coding Plan Pro subscription

Official API and platform for Zhipu AI's open-source GLM models. GLM-5.2 avai...

$30.0

/MONTH

Z.ai Coding Plan Max subscription

Official API and platform for Zhipu AI's open-source GLM models. GLM-5.2 avai...

$80.0

/MONTH

Coding alternatives

Hosted coding assistants for comparison - per seat

Cursor Hobby

AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...

$0.0

/MONTH

GitHub Copilot Individual

AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...

$10.0

/MONTH

GitHub Copilot Business

AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...

$19.0

/MONTH

Cursor Pro

AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...

$20.0

/MONTH

GitHub Copilot Enterprise

AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...

$39.0

/MONTH

Cursor Business

AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...

$40.0

/MONTH

Per-token monthly figures are estimates at typical usage. Prices verified periodically - always confirm current pricing on the provider's website.

On a monthly budget? Compare owning hardware vs renting cloud →