Tokenstead - Find the right AI model for your hardware

RTX PRO 5500 Blackwell 84GB

91 models / sorted by best_quality

Quality Fastest Least mem Newest

Model Fit Speed Memory Scores / Run

Runs comfortably

Ornith-1.5-35B-A3B Q4_K_M

21.7GB 262k ctx

Runs comfortably

425 tok/s

ⓘ estimated

22 / 84GB

91 / 89 / 86

FIT Runs comfortably

SPEED 425 tok/s

ⓘ estimated

MEMORY 22/84GB

Ornith-1.5-35B-A3B BF16

71.1GB 262k ctx

Runs comfortably

130 tok/s

ⓘ estimated

71 / 84GB

91 / 89 / 86

FIT Runs comfortably

SPEED 130 tok/s

ⓘ estimated

MEMORY 71/84GB

Ornith-1.5-35B-A3B Q8_0

37.8GB 262k ctx

Runs comfortably

244 tok/s

ⓘ estimated

38 / 84GB

91 / 89 / 86

FIT Runs comfortably

SPEED 244 tok/s

ⓘ estimated

MEMORY 38/84GB

Ornith-1.5-35B-A3B Q5_K_M

25.3GB 262k ctx

Runs comfortably

364 tok/s

ⓘ estimated

25 / 84GB

91 / 89 / 86

FIT Runs comfortably

SPEED 364 tok/s

ⓘ estimated

MEMORY 25/84GB

Ornith-1.5-35B-A3B Q6_K

29.2GB 262k ctx

Runs comfortably

316 tok/s

ⓘ estimated

29 / 84GB

91 / 89 / 86

FIT Runs comfortably

SPEED 316 tok/s

ⓘ estimated

MEMORY 29/84GB

Qwen3.6 35B A3B Q8_0

37.0GB 262k ctx

Runs comfortably

242 tok/s

ⓘ estimated

37 / 84GB

90 / 91 / 87

FIT Runs comfortably

SPEED 242 tok/s

ⓘ estimated

MEMORY 37/84GB

Qwen3.6 35B A3B Q4_K_M

20.0GB 262k ctx

Runs comfortably

448 tok/s

ⓘ estimated

20 / 84GB

90 / 91 / 87

FIT Runs comfortably

SPEED 448 tok/s

ⓘ estimated

MEMORY 20/84GB

Pokee-Isaac 28B FP16

56.0GB 10000k ctx

Runs comfortably

14 tok/s

ⓘ estimated

56 / 84GB

90 / 88 / 88

FIT Runs comfortably

SPEED 14 tok/s

ⓘ estimated

MEMORY 56/84GB

Pokee-Isaac 28B Q8_0

28.0GB 10000k ctx

Runs comfortably

27 tok/s

ⓘ estimated

28 / 84GB

90 / 88 / 88

FIT Runs comfortably

SPEED 27 tok/s

ⓘ estimated

MEMORY 28/84GB

Pokee-Isaac 28B Q4_K_M

16.0GB 10000k ctx

Runs comfortably

48 tok/s

ⓘ estimated

16 / 84GB

90 / 88 / 88

FIT Runs comfortably

SPEED 48 tok/s

ⓘ estimated

MEMORY 16/84GB

Qwen3 235B A22B Q2_K

68.0GB 128k ctx

Runs comfortably

121 tok/s

ⓘ estimated

68 / 84GB

88 / 90 / 85

FIT Runs comfortably

SPEED 121 tok/s

ⓘ estimated

MEMORY 68/84GB

Qwen3.8-27B NVFP4 Unsloth

15.2GB 262k ctx

Runs comfortably

51 tok/s

ⓘ estimated

15 / 84GB

88 / 89 / 85

FIT Runs comfortably

SPEED 51 tok/s

ⓘ estimated

MEMORY 15/84GB

Qwen3.8-27B UD-Q4_K_XL Unsloth

17.6GB 262k ctx

Runs comfortably

44 tok/s

ⓘ estimated

18 / 84GB

88 / 89 / 85

FIT Runs comfortably

SPEED 44 tok/s

ⓘ estimated

MEMORY 18/84GB

Qwen3.8-27B UD-Q2_K_XL Unsloth

9.8GB 262k ctx

Runs comfortably

78 tok/s

ⓘ estimated

10 / 84GB

88 / 89 / 85

FIT Runs comfortably

SPEED 78 tok/s

ⓘ estimated

MEMORY 10/84GB

Qwen3.8-27B UD-IQ1_S Unsloth

6.2GB 262k ctx

Runs comfortably

124 tok/s

ⓘ estimated

6 / 84GB

88 / 89 / 85

FIT Runs comfortably

SPEED 124 tok/s

ⓘ estimated

MEMORY 6/84GB

Gemma 4 31B NVFP4

16.0GB 256k ctx

Runs comfortably

48 tok/s

ⓘ estimated

16 / 84GB

86 / 89 / 85

FIT Runs comfortably

SPEED 48 tok/s

ⓘ estimated

MEMORY 16/84GB

Gemma 4 31B BF16

61.4GB 256k ctx

Runs comfortably

13 tok/s

ⓘ estimated

61 / 84GB

86 / 89 / 85

FIT Runs comfortably

SPEED 13 tok/s

ⓘ estimated

MEMORY 61/84GB

Gemma 4 31B Q8_0

32.6GB 256k ctx

Runs comfortably

24 tok/s

ⓘ estimated

33 / 84GB

86 / 89 / 85

FIT Runs comfortably

SPEED 24 tok/s

ⓘ estimated

MEMORY 33/84GB

Gemma 4 31B Q4_K_M

18.3GB 256k ctx

Runs comfortably

42 tok/s

ⓘ estimated

18 / 84GB

86 / 89 / 85

FIT Runs comfortably

SPEED 42 tok/s

ⓘ estimated

MEMORY 18/84GB

Gemma 4 31B QAT

18.0GB 256k ctx

Runs comfortably

43 tok/s

ⓘ estimated

18 / 84GB

86 / 89 / 85

FIT Runs comfortably

SPEED 43 tok/s

ⓘ estimated

MEMORY 18/84GB

Gemma 4 26B A4B NVFP4

14.0GB 256k ctx

Runs comfortably

364 tok/s

ⓘ estimated

14 / 84GB

85 / 88 / 84

FIT Runs comfortably

SPEED 364 tok/s

ⓘ estimated

MEMORY 14/84GB

Gemma 4 26B A4B BF16

50.0GB 256k ctx

Runs comfortably

102 tok/s

ⓘ estimated

50 / 84GB

85 / 88 / 84

FIT Runs comfortably

SPEED 102 tok/s

ⓘ estimated

MEMORY 50/84GB

Gemma 4 26B A4B Q8_0

25.0GB 256k ctx

Runs comfortably

204 tok/s

ⓘ estimated

25 / 84GB

85 / 88 / 84

FIT Runs comfortably

SPEED 204 tok/s

ⓘ estimated

MEMORY 25/84GB

Gemma 4 26B A4B Q4_K_M

13.0GB 256k ctx

Runs comfortably

392 tok/s

ⓘ estimated

13 / 84GB

85 / 88 / 84

FIT Runs comfortably

SPEED 392 tok/s

ⓘ estimated

MEMORY 13/84GB

Qwen3.6 27B Q4_K_M

16.5GB 128k ctx

Runs comfortably

47 tok/s

ⓘ estimated

17 / 84GB

85 / 87 / 82

FIT Runs comfortably

SPEED 47 tok/s

ⓘ estimated

MEMORY 17/84GB

Qwen3.6 27B Q8_0

28.0GB 128k ctx

Runs comfortably

27 tok/s

ⓘ estimated

28 / 84GB

85 / 87 / 82

FIT Runs comfortably

SPEED 27 tok/s

ⓘ estimated

MEMORY 28/84GB

Qwen3 32B Q6_K

28.5GB 128k ctx

Runs comfortably

27 tok/s

ⓘ estimated

29 / 84GB

80 / 82 / 78

FIT Runs comfortably

SPEED 27 tok/s

ⓘ estimated

MEMORY 29/84GB

Qwen3 32B Q4_K_M

20.0GB 128k ctx

Runs comfortably

38 tok/s

ⓘ estimated

20 / 84GB

80 / 82 / 78

FIT Runs comfortably

SPEED 38 tok/s

ⓘ estimated

MEMORY 20/84GB

Qwen3 32B Q5_K_M

24.5GB 128k ctx

Runs comfortably

31 tok/s

ⓘ estimated

25 / 84GB

80 / 82 / 78

FIT Runs comfortably

SPEED 31 tok/s

ⓘ estimated

MEMORY 25/84GB

Qwen3 32B Q8_0

34.0GB 128k ctx

Runs comfortably

23 tok/s

ⓘ estimated

34 / 84GB

80 / 82 / 78

FIT Runs comfortably

SPEED 23 tok/s

ⓘ estimated

MEMORY 34/84GB

Ornith-1.5-9B BF16

18.4GB 262k ctx

Runs comfortably

42 tok/s

ⓘ estimated

18 / 84GB

78 / 76 / 74

FIT Runs comfortably

SPEED 42 tok/s

ⓘ estimated

MEMORY 18/84GB

Ornith-1.5-9B Q8_0

9.8GB 262k ctx

Runs comfortably

79 tok/s

ⓘ estimated

10 / 84GB

78 / 76 / 74

FIT Runs comfortably

SPEED 79 tok/s

ⓘ estimated

MEMORY 10/84GB

Nemotron 3.5 Lightning Q4_K_M

32.0GB 1000k ctx

Runs comfortably

211 tok/s

ⓘ estimated

32 / 84GB

78 / 76 / 74

FIT Runs comfortably

SPEED 211 tok/s

ⓘ estimated

MEMORY 32/84GB

Ornith-1.5-9B Q4_K_M

5.8GB 262k ctx

Runs comfortably

133 tok/s

ⓘ estimated

6 / 84GB

78 / 76 / 74

FIT Runs comfortably

SPEED 133 tok/s

ⓘ estimated

MEMORY 6/84GB

Ornith-1.5-9B Q5_K_M

6.6GB 262k ctx

Runs comfortably

116 tok/s

ⓘ estimated

7 / 84GB

78 / 76 / 74

FIT Runs comfortably

SPEED 116 tok/s

ⓘ estimated

MEMORY 7/84GB

Ornith-1.5-9B Q6_K

7.6GB 262k ctx

Runs comfortably

102 tok/s

ⓘ estimated

8 / 84GB

78 / 76 / 74

FIT Runs comfortably

SPEED 102 tok/s

ⓘ estimated

MEMORY 8/84GB

Nemotron 3.5 Lightning FP16

60.0GB 1000k ctx

Runs comfortably

112 tok/s

ⓘ estimated

60 / 84GB

78 / 76 / 74

FIT Runs comfortably

SPEED 112 tok/s

ⓘ estimated

MEMORY 60/84GB

Nemotron 3.5 Lightning Q8_0

58.0GB 1000k ctx

Runs comfortably

116 tok/s

ⓘ estimated

58 / 84GB

78 / 76 / 74

FIT Runs comfortably

SPEED 116 tok/s

ⓘ estimated

MEMORY 58/84GB

Qwen3 30B A3B Q8_0

31.0GB 128k ctx

Runs comfortably

252 tok/s

ⓘ estimated

31 / 84GB

75 / 78 / 72

FIT Runs comfortably

SPEED 252 tok/s

ⓘ estimated

MEMORY 31/84GB

Qwen3 30B A3B Q4_K_M

15.5GB 128k ctx

Runs comfortably

504 tok/s

ⓘ estimated

16 / 84GB

75 / 78 / 72

FIT Runs comfortably

SPEED 504 tok/s

ⓘ estimated

MEMORY 16/84GB

Phi-4 14B Q4_K_M

8.5GB 16k ctx

Runs comfortably

90 tok/s

ⓘ estimated

9 / 84GB

75 / 78 / 70

FIT Runs comfortably

SPEED 90 tok/s

ⓘ estimated

MEMORY 9/84GB

Phi-4 14B FP16

29.0GB 16k ctx

Runs comfortably

27 tok/s

ⓘ estimated

29 / 84GB

75 / 78 / 70

FIT Runs comfortably

SPEED 27 tok/s

ⓘ estimated

MEMORY 29/84GB

Phi-4 14B Q8_0

15.0GB 16k ctx

Runs comfortably

51 tok/s

ⓘ estimated

15 / 84GB

75 / 78 / 70

FIT Runs comfortably

SPEED 51 tok/s

ⓘ estimated

MEMORY 15/84GB

Xing4.0-29B-A4B BF16

62.4GB 16k cap

Runs comfortably

57 tok/s

ⓘ estimated

62 / 84GB

75 / 73 / 72

FIT Runs comfortably

SPEED 57 tok/s

ⓘ estimated

MEMORY 62/84GB

Xing4.0-29B-A4B Q4_K_M

20.1GB 57k cap

Runs comfortably

100 tok/s

ⓘ estimated

20 / 84GB

75 / 73 / 72

FIT Runs comfortably

SPEED 100 tok/s

ⓘ estimated

MEMORY 20/84GB

Llama 3.3 70B Instruct Q3_K_M

30.0GB 128k ctx

Runs comfortably

26 tok/s

ⓘ estimated

30 / 84GB

72 / 77 / 80

FIT Runs comfortably

SPEED 26 tok/s

ⓘ estimated

MEMORY 30/84GB

Llama 3.3 70B Instruct Q2_K

21.5GB 128k ctx

Runs comfortably

36 tok/s

ⓘ estimated

22 / 84GB

72 / 77 / 80

FIT Runs comfortably

SPEED 36 tok/s

ⓘ estimated

MEMORY 22/84GB

Llama 3.3 70B Instruct Q8_0

74.0GB 128k ctx

Runs comfortably

10 tok/s

ⓘ estimated

74 / 84GB

72 / 77 / 80

FIT Runs comfortably

SPEED 10 tok/s

ⓘ estimated

MEMORY 74/84GB

Llama 3.3 70B Instruct Q4_K_M

42.0GB 128k ctx

Runs comfortably

18 tok/s

ⓘ estimated

42 / 84GB

72 / 77 / 80

FIT Runs comfortably

SPEED 18 tok/s

ⓘ estimated

MEMORY 42/84GB

Qwen3 14B Q8_0

15.0GB 128k ctx

Runs comfortably

51 tok/s

ⓘ estimated

15 / 84GB

72 / 75 / 70

FIT Runs comfortably

SPEED 51 tok/s

ⓘ estimated

MEMORY 15/84GB

Qwen3 14B Q4_K_M

9.0GB 128k ctx

Runs comfortably

85 tok/s

ⓘ estimated

9 / 84GB

72 / 75 / 70

FIT Runs comfortably

SPEED 85 tok/s

ⓘ estimated

MEMORY 9/84GB

Gemma 4 12B Q4_K_M

7.2GB 128k ctx

Runs comfortably

107 tok/s

ⓘ estimated

7 / 84GB

70 / 74 / 72

FIT Runs comfortably

SPEED 107 tok/s

ⓘ estimated

MEMORY 7/84GB

Gemma 4 12B Q8_0

13.0GB 128k ctx

Runs comfortably

59 tok/s

ⓘ estimated

13 / 84GB

70 / 74 / 72

FIT Runs comfortably

SPEED 59 tok/s

ⓘ estimated

MEMORY 13/84GB

Gemma 3 27B Q8_0

28.0GB 128k ctx

Runs comfortably

27 tok/s

ⓘ estimated

28 / 84GB

68 / 71 / 72

FIT Runs comfortably

SPEED 27 tok/s

ⓘ estimated

MEMORY 28/84GB

Gemma 3 27B Q4_K_M

17.0GB 128k ctx

Runs comfortably

45 tok/s

ⓘ estimated

17 / 84GB

68 / 71 / 72

FIT Runs comfortably

SPEED 45 tok/s

ⓘ estimated

MEMORY 17/84GB

Qwen3 8B Q4_K_M

5.2GB 128k ctx

Runs comfortably

148 tok/s

ⓘ estimated

5 / 84GB

67 / 70 / 65

FIT Runs comfortably

SPEED 148 tok/s

ⓘ estimated

MEMORY 5/84GB

Qwen3 8B Q8_0

8.5GB 128k ctx

Runs comfortably

90 tok/s

ⓘ estimated

9 / 84GB

67 / 70 / 65

FIT Runs comfortably

SPEED 90 tok/s

ⓘ estimated

MEMORY 9/84GB

Mixtral 8x7B Instruct Q4_K_M

26.5GB 32k ctx

Runs comfortably

105 tok/s

ⓘ estimated

27 / 84GB

62 / 65 / 68

FIT Runs comfortably

SPEED 105 tok/s

ⓘ estimated

MEMORY 27/84GB

Mixtral 8x7B Instruct Q3_K_M

19.0GB 32k ctx

Runs comfortably

146 tok/s

ⓘ estimated

19 / 84GB

62 / 65 / 68

FIT Runs comfortably

SPEED 146 tok/s

ⓘ estimated

MEMORY 19/84GB

Gemma 3 12B Q8_0

13.5GB 128k ctx

Runs comfortably

57 tok/s

ⓘ estimated

14 / 84GB

62 / 65 / 68

FIT Runs comfortably

SPEED 57 tok/s

ⓘ estimated

MEMORY 14/84GB

Gemma 3 12B Q4_K_M

7.5GB 128k ctx

Runs comfortably

103 tok/s

ⓘ estimated

8 / 84GB

62 / 65 / 68

FIT Runs comfortably

SPEED 103 tok/s

ⓘ estimated

MEMORY 8/84GB

Mistral Nemo 12B Q8_0

13.2GB 128k ctx

Runs comfortably

58 tok/s

ⓘ estimated

13 / 84GB

58 / 60 / 62

FIT Runs comfortably

SPEED 58 tok/s

ⓘ estimated

MEMORY 13/84GB

Mistral Nemo 12B Q4_K_M

7.3GB 128k ctx

Runs comfortably

105 tok/s

ⓘ estimated

7 / 84GB

58 / 60 / 62

FIT Runs comfortably

SPEED 105 tok/s

ⓘ estimated

MEMORY 7/84GB

Qwen3 4B Q4_K_M

2.6GB 32k ctx

Runs comfortably

296 tok/s

ⓘ estimated

3 / 84GB

58 / 60 / 56

FIT Runs comfortably

SPEED 296 tok/s

ⓘ estimated

MEMORY 3/84GB

Phi-4 Mini Q8_0

4.1GB 128k ctx

Runs comfortably

188 tok/s

ⓘ estimated

4 / 84GB

55 / 58 / 52

FIT Runs comfortably

SPEED 188 tok/s

ⓘ estimated

MEMORY 4/84GB

Phi-4 Mini Q4_K_M

2.5GB 128k ctx

Runs comfortably

307 tok/s

ⓘ estimated

3 / 84GB

55 / 58 / 52

FIT Runs comfortably

SPEED 307 tok/s

ⓘ estimated

MEMORY 3/84GB

Llama 3.1 8B Instruct FP16

16.0GB 128k ctx

Runs comfortably

48 tok/s

ⓘ estimated

16 / 84GB

52 / 55 / 62

FIT Runs comfortably

SPEED 48 tok/s

ⓘ estimated

MEMORY 16/84GB

Llama 3.1 8B Instruct Q8_0

8.0GB 128k ctx

Runs comfortably

96 tok/s

ⓘ estimated

8 / 84GB

52 / 55 / 62

FIT Runs comfortably

SPEED 96 tok/s

ⓘ estimated

MEMORY 8/84GB

Llama 3.1 8B Instruct Q4_K_M

4.5GB 128k ctx

Runs comfortably

171 tok/s

ⓘ estimated

5 / 84GB

52 / 55 / 62

FIT Runs comfortably

SPEED 171 tok/s

ⓘ estimated

MEMORY 5/84GB

Gemma 3 4B Q4_K_M

3.0GB 128k ctx

Runs comfortably

256 tok/s

ⓘ estimated

3 / 84GB

42 / 45 / 55

FIT Runs comfortably

SPEED 256 tok/s

ⓘ estimated

MEMORY 3/84GB

Gemma 3 4B Q8_0

5.0GB 128k ctx

Runs comfortably

154 tok/s

ⓘ estimated

5 / 84GB

42 / 45 / 55

FIT Runs comfortably

SPEED 154 tok/s

ⓘ estimated

MEMORY 5/84GB

Llama 3.2 3B Instruct Q8_0

3.5GB 128k ctx

Runs comfortably

220 tok/s

ⓘ estimated

4 / 84GB

35 / 38 / 50

FIT Runs comfortably

SPEED 220 tok/s

ⓘ estimated

MEMORY 4/84GB

Llama 3.2 3B Instruct Q4_K_M

2.0GB 128k ctx

Runs comfortably

384 tok/s

ⓘ estimated

2 / 84GB

35 / 38 / 50

FIT Runs comfortably

SPEED 384 tok/s

ⓘ estimated

MEMORY 2/84GB

Mellum2.1 12B Thinking Q4_K_M

7.0GB 131k ctx

Runs comfortably

462 tok/s

ⓘ estimated

7 / 84GB

FIT Runs comfortably

SPEED 462 tok/s

ⓘ estimated

MEMORY 7/84GB

Mellum2.1 12B Thinking FP16

24.3GB 131k ctx

Runs comfortably

147 tok/s

ⓘ estimated

24 / 84GB

FIT Runs comfortably

SPEED 147 tok/s

ⓘ estimated

MEMORY 24/84GB

Muse Glimmer 30B Q8_0

33.0GB 80k cap

Runs comfortably

22 tok/s

ⓘ estimated

33 / 84GB

FIT Runs comfortably

SPEED 22 tok/s

ⓘ estimated

MEMORY 33/84GB

Muse Glimmer 30B Q4_K_M

18.0GB 100k cap

Runs comfortably

38 tok/s

ⓘ estimated

18 / 84GB

FIT Runs comfortably

SPEED 38 tok/s

ⓘ estimated

MEMORY 18/84GB

LFM2.5-24B-A2B FP8

24.0GB 131k ctx

Runs comfortably

331 tok/s

ⓘ estimated

24 / 84GB

FIT Runs comfortably

SPEED 331 tok/s

ⓘ estimated

MEMORY 24/84GB

LFM2.5-24B-A2B Q4_K_M

13.7GB 131k ctx

Runs comfortably

526 tok/s

ⓘ estimated

14 / 84GB

FIT Runs comfortably

SPEED 526 tok/s

ⓘ estimated

MEMORY 14/84GB

Runs tight

Qwen3.8-Flash-Next UD-IQ1_S Unsloth

72.5GB 262k ctx

Runs tight

318 tok/s

ⓘ estimated

73 / 84GB

92 / 92 / 89

FIT Runs tight

SPEED 318 tok/s

ⓘ estimated

MEMORY 73/84GB

Qwen3.8-Flash-Next EXL3_2BPW

62.7GB 142k cap

Runs tight

202 tok/s

ⓘ estimated

63 / 84GB

92 / 92 / 89

FIT Runs tight

SPEED 202 tok/s

ⓘ estimated

MEMORY 63/84GB

MiMo-V2.6-Flash Q2_K

77.0GB 1k cap

Runs tight

38 tok/s

ⓘ estimated

77 / 84GB

78 / 77 / 76

FIT Runs tight

SPEED 38 tok/s

ⓘ estimated

MEMORY 77/84GB

MiniMax M2.7 UD-Q2_K_XL Unsloth

75.3GB 35k cap

Runs tight

10 tok/s

ⓘ estimated

75 / 84GB

FIT Runs tight

SPEED 10 tok/s

ⓘ estimated

MEMORY 75/84GB

MiniMax M2.7 UD-IQ1_M Unsloth

60.7GB 93k cap

Runs tight

12 tok/s

ⓘ estimated

61 / 84GB

FIT Runs tight

SPEED 12 tok/s

ⓘ estimated

MEMORY 61/84GB

Runs with CPU offload

GLM-5.3-Flash UD-IQ1_S Unsloth

93.1GB 0k cap

Runs with CPU offload

147 tok/s

ⓘ estimated

93 / 84GB

93 / 92 / 91

FIT Runs with CPU offload

SPEED 147 tok/s

ⓘ estimated

MEMORY 93/84GB

GLM-5.3-Flash UD-Q2_K_XL Unsloth

109.0GB 0k cap

Runs with CPU offload

125 tok/s

ⓘ estimated

109 / 84GB

93 / 92 / 91

FIT Runs with CPU offload

SPEED 125 tok/s

ⓘ estimated

MEMORY 109/84GB

GLM-5.3-Flash UD-IQ3_XXS Unsloth

120.0GB 0k cap

Runs with CPU offload

114 tok/s

ⓘ estimated

120 / 84GB

93 / 92 / 91

FIT Runs with CPU offload

SPEED 114 tok/s

ⓘ estimated

MEMORY 120/84GB

Qwen3.8-Flash-Next EXL3_3BPW

85.0GB 142k cap

Runs with CPU offload

169 tok/s

ⓘ estimated

85 / 84GB

92 / 92 / 89

FIT Runs with CPU offload

SPEED 169 tok/s

ⓘ estimated

MEMORY 85/84GB

Qwen3 235B A22B Q4_K_M

125.0GB 0k cap

Runs with CPU offload

66 tok/s

ⓘ estimated

125 / 84GB

88 / 90 / 85

FIT Runs with CPU offload

SPEED 66 tok/s

ⓘ estimated

MEMORY 125/84GB

MiniMax M3 UD-IQ1_M Unsloth

128.4GB 0k cap

Runs with CPU offload

6 tok/s

ⓘ estimated

128 / 84GB

FIT Runs with CPU offload

SPEED 6 tok/s

ⓘ estimated

MEMORY 128/84GB

Muse Glimmer 30B FP16

60.0GB 0k cap

Runs with CPU offload

12 tok/s

ⓘ estimated

60 / 84GB

FIT Runs with CPU offload

SPEED 12 tok/s

ⓘ estimated

MEMORY 60/84GB

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 →