Tokenstead - Find the right AI model for your hardware

RTX 3090 Ti 24GB

68 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

306 tok/s

ⓘ estimated

22 / 24GB

91 / 89 / 86

FIT Runs comfortably

SPEED 306 tok/s

ⓘ estimated

MEMORY 22/24GB

Qwen3.6 35B A3B Q4_K_M

20.0GB 262k ctx

Runs comfortably

323 tok/s

ⓘ estimated

20 / 24GB

90 / 91 / 87

FIT Runs comfortably

SPEED 323 tok/s

ⓘ estimated

MEMORY 20/24GB

Pokee-Isaac 28B Q4_K_M

16.0GB 10000k ctx

Runs comfortably

35 tok/s

ⓘ estimated

16 / 24GB

90 / 88 / 88

FIT Runs comfortably

SPEED 35 tok/s

ⓘ estimated

MEMORY 16/24GB

Qwen3.8-27B UD-IQ1_S Unsloth

6.2GB 262k ctx

Runs comfortably

90 tok/s

ⓘ estimated

6 / 24GB

88 / 89 / 85

FIT Runs comfortably

SPEED 90 tok/s

ⓘ estimated

MEMORY 6/24GB

Qwen3.8-27B UD-Q2_K_XL Unsloth

9.8GB 262k ctx

Runs comfortably

56 tok/s

ⓘ estimated

10 / 24GB

88 / 89 / 85

FIT Runs comfortably

SPEED 56 tok/s

ⓘ estimated

MEMORY 10/24GB

Qwen3.8-27B UD-Q4_K_XL Unsloth

17.6GB 262k ctx

Runs comfortably

32 tok/s

ⓘ estimated

18 / 24GB

88 / 89 / 85

FIT Runs comfortably

SPEED 32 tok/s

ⓘ estimated

MEMORY 18/24GB

Gemma 4 31B QAT

18.0GB 256k ctx

Runs comfortably

31 tok/s

ⓘ estimated

18 / 24GB

86 / 89 / 85

FIT Runs comfortably

SPEED 31 tok/s

ⓘ estimated

MEMORY 18/24GB

Gemma 4 31B Q4_K_M

18.3GB 256k ctx

Runs comfortably

30 tok/s

ⓘ estimated

18 / 24GB

86 / 89 / 85

FIT Runs comfortably

SPEED 30 tok/s

ⓘ estimated

MEMORY 18/24GB

Gemma 4 26B A4B Q4_K_M

13.0GB 256k ctx

Runs comfortably

282 tok/s

ⓘ estimated

13 / 24GB

85 / 88 / 84

FIT Runs comfortably

SPEED 282 tok/s

ⓘ estimated

MEMORY 13/24GB

Qwen3.6 27B Q4_K_M

16.5GB 128k ctx

Runs comfortably

34 tok/s

ⓘ estimated

17 / 24GB

85 / 87 / 82

FIT Runs comfortably

SPEED 34 tok/s

ⓘ estimated

MEMORY 17/24GB

Qwen3 32B Q4_K_M

20.0GB 128k ctx

Runs comfortably

28 tok/s

ⓘ estimated

20 / 24GB

80 / 82 / 78

FIT Runs comfortably

SPEED 28 tok/s

ⓘ estimated

MEMORY 20/24GB

Ornith-1.5-9B Q4_K_M

5.8GB 262k ctx

Runs comfortably

96 tok/s

ⓘ estimated

6 / 24GB

78 / 76 / 74

FIT Runs comfortably

SPEED 96 tok/s

ⓘ estimated

MEMORY 6/24GB

Ornith-1.5-9B Q5_K_M

6.6GB 262k ctx

Runs comfortably

83 tok/s

ⓘ estimated

7 / 24GB

78 / 76 / 74

FIT Runs comfortably

SPEED 83 tok/s

ⓘ estimated

MEMORY 7/24GB

Ornith-1.5-9B Q6_K

7.6GB 262k ctx

Runs comfortably

73 tok/s

ⓘ estimated

8 / 24GB

78 / 76 / 74

FIT Runs comfortably

SPEED 73 tok/s

ⓘ estimated

MEMORY 8/24GB

Ornith-1.5-9B BF16

18.4GB 262k ctx

Runs comfortably

30 tok/s

ⓘ estimated

18 / 24GB

78 / 76 / 74

FIT Runs comfortably

SPEED 30 tok/s

ⓘ estimated

MEMORY 18/24GB

Ornith-1.5-9B Q8_0

9.8GB 262k ctx

Runs comfortably

57 tok/s

ⓘ estimated

10 / 24GB

78 / 76 / 74

FIT Runs comfortably

SPEED 57 tok/s

ⓘ estimated

MEMORY 10/24GB

Qwen3 30B A3B Q4_K_M

15.5GB 128k ctx

Runs comfortably

363 tok/s

ⓘ estimated

16 / 24GB

75 / 78 / 72

FIT Runs comfortably

SPEED 363 tok/s

ⓘ estimated

MEMORY 16/24GB

Phi-4 14B Q4_K_M

8.5GB 16k ctx

Runs comfortably

65 tok/s

ⓘ estimated

9 / 24GB

75 / 78 / 70

FIT Runs comfortably

SPEED 65 tok/s

ⓘ estimated

MEMORY 9/24GB

Phi-4 14B Q8_0

15.0GB 16k ctx

Runs comfortably

37 tok/s

ⓘ estimated

15 / 24GB

75 / 78 / 70

FIT Runs comfortably

SPEED 37 tok/s

ⓘ estimated

MEMORY 15/24GB

Xing4.0-29B-A4B Q4_K_M

20.1GB 7k cap

Runs comfortably

72 tok/s

ⓘ estimated

20 / 24GB

75 / 73 / 72

FIT Runs comfortably

SPEED 72 tok/s

ⓘ estimated

MEMORY 20/24GB

Qwen3 14B Q4_K_M

9.0GB 128k ctx

Runs comfortably

62 tok/s

ⓘ estimated

9 / 24GB

72 / 75 / 70

FIT Runs comfortably

SPEED 62 tok/s

ⓘ estimated

MEMORY 9/24GB

Qwen3 14B Q8_0

15.0GB 128k ctx

Runs comfortably

37 tok/s

ⓘ estimated

15 / 24GB

72 / 75 / 70

FIT Runs comfortably

SPEED 37 tok/s

ⓘ estimated

MEMORY 15/24GB

Gemma 4 12B Q8_0

13.0GB 128k ctx

Runs comfortably

43 tok/s

ⓘ estimated

13 / 24GB

70 / 74 / 72

FIT Runs comfortably

SPEED 43 tok/s

ⓘ estimated

MEMORY 13/24GB

Gemma 4 12B Q4_K_M

7.2GB 128k ctx

Runs comfortably

77 tok/s

ⓘ estimated

7 / 24GB

70 / 74 / 72

FIT Runs comfortably

SPEED 77 tok/s

ⓘ estimated

MEMORY 7/24GB

Gemma 3 27B Q4_K_M

17.0GB 128k ctx

Runs comfortably

33 tok/s

ⓘ estimated

17 / 24GB

68 / 71 / 72

FIT Runs comfortably

SPEED 33 tok/s

ⓘ estimated

MEMORY 17/24GB

Qwen3 8B Q4_K_M

5.2GB 128k ctx

Runs comfortably

107 tok/s

ⓘ estimated

5 / 24GB

67 / 70 / 65

FIT Runs comfortably

SPEED 107 tok/s

ⓘ estimated

MEMORY 5/24GB

Qwen3 8B Q8_0

8.5GB 128k ctx

Runs comfortably

65 tok/s

ⓘ estimated

9 / 24GB

67 / 70 / 65

FIT Runs comfortably

SPEED 65 tok/s

ⓘ estimated

MEMORY 9/24GB

Mixtral 8x7B Instruct Q3_K_M

19.0GB 32k ctx

Runs comfortably

106 tok/s

ⓘ estimated

19 / 24GB

62 / 65 / 68

FIT Runs comfortably

SPEED 106 tok/s

ⓘ estimated

MEMORY 19/24GB

Gemma 3 12B Q8_0

13.5GB 128k ctx

Runs comfortably

41 tok/s

ⓘ estimated

14 / 24GB

62 / 65 / 68

FIT Runs comfortably

SPEED 41 tok/s

ⓘ estimated

MEMORY 14/24GB

Gemma 3 12B Q4_K_M

7.5GB 128k ctx

Runs comfortably

74 tok/s

ⓘ estimated

8 / 24GB

62 / 65 / 68

FIT Runs comfortably

SPEED 74 tok/s

ⓘ estimated

MEMORY 8/24GB

Mistral Nemo 12B Q8_0

13.2GB 128k ctx

Runs comfortably

42 tok/s

ⓘ estimated

13 / 24GB

58 / 60 / 62

FIT Runs comfortably

SPEED 42 tok/s

ⓘ estimated

MEMORY 13/24GB

Mistral Nemo 12B Q4_K_M

7.3GB 128k ctx

Runs comfortably

76 tok/s

ⓘ estimated

7 / 24GB

58 / 60 / 62

FIT Runs comfortably

SPEED 76 tok/s

ⓘ estimated

MEMORY 7/24GB

Qwen3 4B Q4_K_M

2.6GB 32k ctx

Runs comfortably

213 tok/s

ⓘ estimated

3 / 24GB

58 / 60 / 56

FIT Runs comfortably

SPEED 213 tok/s

ⓘ estimated

MEMORY 3/24GB

Phi-4 Mini Q8_0

4.1GB 128k ctx

Runs comfortably

135 tok/s

ⓘ estimated

4 / 24GB

55 / 58 / 52

FIT Runs comfortably

SPEED 135 tok/s

ⓘ estimated

MEMORY 4/24GB

Phi-4 Mini Q4_K_M

2.5GB 128k ctx

Runs comfortably

222 tok/s

ⓘ estimated

3 / 24GB

55 / 58 / 52

FIT Runs comfortably

SPEED 222 tok/s

ⓘ estimated

MEMORY 3/24GB

Llama 3.1 8B Instruct FP16

16.0GB 128k ctx

Runs comfortably

35 tok/s

ⓘ estimated

16 / 24GB

52 / 55 / 62

FIT Runs comfortably

SPEED 35 tok/s

ⓘ estimated

MEMORY 16/24GB

Llama 3.1 8B Instruct Q8_0

8.0GB 128k ctx

Runs comfortably

69 tok/s

ⓘ estimated

8 / 24GB

52 / 55 / 62

FIT Runs comfortably

SPEED 69 tok/s

ⓘ estimated

MEMORY 8/24GB

Llama 3.1 8B Instruct Q4_K_M

4.5GB 128k ctx

Runs comfortably

123 tok/s

ⓘ estimated

5 / 24GB

52 / 55 / 62

FIT Runs comfortably

SPEED 123 tok/s

ⓘ estimated

MEMORY 5/24GB

Gemma 3 4B Q8_0

5.0GB 128k ctx

Runs comfortably

111 tok/s

ⓘ estimated

5 / 24GB

42 / 45 / 55

FIT Runs comfortably

SPEED 111 tok/s

ⓘ estimated

MEMORY 5/24GB

Gemma 3 4B Q4_K_M

3.0GB 128k ctx

Runs comfortably

185 tok/s

ⓘ estimated

3 / 24GB

42 / 45 / 55

FIT Runs comfortably

SPEED 185 tok/s

ⓘ estimated

MEMORY 3/24GB

Llama 3.2 3B Instruct Q4_K_M

2.0GB 128k ctx

Runs comfortably

277 tok/s

ⓘ estimated

2 / 24GB

35 / 38 / 50

FIT Runs comfortably

SPEED 277 tok/s

ⓘ estimated

MEMORY 2/24GB

Llama 3.2 3B Instruct Q8_0

3.5GB 128k ctx

Runs comfortably

158 tok/s

ⓘ estimated

4 / 24GB

35 / 38 / 50

FIT Runs comfortably

SPEED 158 tok/s

ⓘ estimated

MEMORY 4/24GB

Mellum2.1 12B Thinking Q4_K_M

7.0GB 131k ctx

Runs comfortably

333 tok/s

ⓘ estimated

7 / 24GB

FIT Runs comfortably

SPEED 333 tok/s

ⓘ estimated

MEMORY 7/24GB

LFM2.5-24B-A2B Q4_K_M

13.7GB 102k cap

Runs comfortably

379 tok/s

ⓘ estimated

14 / 24GB

FIT Runs comfortably

SPEED 379 tok/s

ⓘ estimated

MEMORY 14/24GB

Runs tight

Llama 3.3 70B Instruct Q2_K

21.5GB 128k ctx

Runs tight

26 tok/s

ⓘ estimated

22 / 24GB

72 / 77 / 80

FIT Runs tight

SPEED 26 tok/s

ⓘ estimated

MEMORY 22/24GB

Muse Glimmer 30B Q4_K_M

18.0GB 0k cap

Runs tight

27 tok/s

ⓘ estimated

18 / 24GB

FIT Runs tight

SPEED 27 tok/s

ⓘ estimated

MEMORY 18/24GB

Runs with CPU offload

Qwen3.8-Flash-Next EXL3_2BPW

62.7GB 0k cap

Runs with CPU offload

146 tok/s

ⓘ estimated

63 / 24GB

92 / 92 / 89

FIT Runs with CPU offload

SPEED 146 tok/s

ⓘ estimated

MEMORY 63/24GB

Qwen3.8-Flash-Next EXL3_3BPW

85.0GB 0k cap

Runs with CPU offload

122 tok/s

ⓘ estimated

85 / 24GB

92 / 92 / 89

FIT Runs with CPU offload

SPEED 122 tok/s

ⓘ estimated

MEMORY 85/24GB

Ornith-1.5-35B-A3B Q8_0

37.8GB 0k cap

Runs with CPU offload

176 tok/s

ⓘ estimated

38 / 24GB

91 / 89 / 86

FIT Runs with CPU offload

SPEED 176 tok/s

ⓘ estimated

MEMORY 38/24GB

Ornith-1.5-35B-A3B Q6_K

29.2GB 0k cap

Runs with CPU offload

228 tok/s

ⓘ estimated

29 / 24GB

91 / 89 / 86

FIT Runs with CPU offload

SPEED 228 tok/s

ⓘ estimated

MEMORY 29/24GB

Ornith-1.5-35B-A3B Q5_K_M

25.3GB 0k cap

Runs with CPU offload

263 tok/s

ⓘ estimated

25 / 24GB

91 / 89 / 86

FIT Runs with CPU offload

SPEED 263 tok/s

ⓘ estimated

MEMORY 25/24GB

Qwen3.6 35B A3B Q8_0

37.0GB 0k cap

Runs with CPU offload

175 tok/s

ⓘ estimated

37 / 24GB

90 / 91 / 87

FIT Runs with CPU offload

SPEED 175 tok/s

ⓘ estimated

MEMORY 37/24GB

Pokee-Isaac 28B Q8_0

28.0GB 0k cap

Runs with CPU offload

20 tok/s

ⓘ estimated

28 / 24GB

90 / 88 / 88

FIT Runs with CPU offload

SPEED 20 tok/s

ⓘ estimated

MEMORY 28/24GB

Gemma 4 31B Q8_0

32.6GB 0k cap

Runs with CPU offload

17 tok/s

ⓘ estimated

33 / 24GB

86 / 89 / 85

FIT Runs with CPU offload

SPEED 17 tok/s

ⓘ estimated

MEMORY 33/24GB

Gemma 4 26B A4B Q8_0

25.0GB 0k cap

Runs with CPU offload

147 tok/s

ⓘ estimated

25 / 24GB

85 / 88 / 84

FIT Runs with CPU offload

SPEED 147 tok/s

ⓘ estimated

MEMORY 25/24GB

Qwen3.6 27B Q8_0

28.0GB 0k cap

Runs with CPU offload

20 tok/s

ⓘ estimated

28 / 24GB

85 / 87 / 82

FIT Runs with CPU offload

SPEED 20 tok/s

ⓘ estimated

MEMORY 28/24GB

Qwen3 32B Q8_0

34.0GB 0k cap

Runs with CPU offload

16 tok/s

ⓘ estimated

34 / 24GB

80 / 82 / 78

FIT Runs with CPU offload

SPEED 16 tok/s

ⓘ estimated

MEMORY 34/24GB

Qwen3 32B Q5_K_M

24.5GB 0k cap

Runs with CPU offload

23 tok/s

ⓘ estimated

25 / 24GB

80 / 82 / 78

FIT Runs with CPU offload

SPEED 23 tok/s

ⓘ estimated

MEMORY 25/24GB

Qwen3 32B Q6_K

28.5GB 0k cap

Runs with CPU offload

19 tok/s

ⓘ estimated

29 / 24GB

80 / 82 / 78

FIT Runs with CPU offload

SPEED 19 tok/s

ⓘ estimated

MEMORY 29/24GB

Nemotron 3.5 Lightning Q4_K_M

32.0GB 0k cap

Runs with CPU offload

152 tok/s

ⓘ estimated

32 / 24GB

78 / 76 / 74

FIT Runs with CPU offload

SPEED 152 tok/s

ⓘ estimated

MEMORY 32/24GB

Qwen3 30B A3B Q8_0

31.0GB 0k cap

Runs with CPU offload

182 tok/s

ⓘ estimated

31 / 24GB

75 / 78 / 72

FIT Runs with CPU offload

SPEED 182 tok/s

ⓘ estimated

MEMORY 31/24GB

Phi-4 14B FP16

29.0GB 0k cap

Runs with CPU offload

19 tok/s

ⓘ estimated

29 / 24GB

75 / 78 / 70

FIT Runs with CPU offload

SPEED 19 tok/s

ⓘ estimated

MEMORY 29/24GB

Llama 3.3 70B Instruct Q3_K_M

30.0GB 0k cap

Runs with CPU offload

18 tok/s

ⓘ estimated

30 / 24GB

72 / 77 / 80

FIT Runs with CPU offload

SPEED 18 tok/s

ⓘ estimated

MEMORY 30/24GB

Gemma 3 27B Q8_0

28.0GB 0k cap

Runs with CPU offload

20 tok/s

ⓘ estimated

28 / 24GB

68 / 71 / 72

FIT Runs with CPU offload

SPEED 20 tok/s

ⓘ estimated

MEMORY 28/24GB

Mixtral 8x7B Instruct Q4_K_M

26.5GB 0k cap

Runs with CPU offload

76 tok/s

ⓘ estimated

27 / 24GB

62 / 65 / 68

FIT Runs with CPU offload

SPEED 76 tok/s

ⓘ estimated

MEMORY 27/24GB

Mellum2.1 12B Thinking FP16

24.3GB 0k cap

Runs with CPU offload

106 tok/s

ⓘ estimated

24 / 24GB

FIT Runs with CPU offload

SPEED 106 tok/s

ⓘ estimated

MEMORY 24/24GB

Muse Glimmer 30B Q8_0

33.0GB 0k cap

Runs with CPU offload

16 tok/s

ⓘ estimated

33 / 24GB

FIT Runs with CPU offload

SPEED 16 tok/s

ⓘ estimated

MEMORY 33/24GB

LFM2.5-24B-A2B FP8

24.0GB 0k cap

Runs with CPU offload

239 tok/s

ⓘ estimated

24 / 24GB

FIT Runs with CPU offload

SPEED 239 tok/s

ⓘ estimated

MEMORY 24/24GB

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 →