Model
Fit
Speed
Memory
Scores / Run
Runs comfortably
Runs comfortably
30 tok/s
ⓘ estimated
38/48GB
Ornith-1.5-35B-A3B
Q4_K_M
21.7GB
47k cap
Runs comfortably
40
tok/s
ⓘ estimated
22
/ 48GB
91
/
89
/
86
Runs comfortably
40 tok/s
ⓘ estimated
22/48GB
Runs comfortably
35 tok/s
ⓘ estimated
29/48GB
Ornith-1.5-35B-A3B
Q5_K_M
25.3GB
40k cap
Runs comfortably
38
tok/s
ⓘ estimated
25
/ 48GB
91
/
89
/
86
Runs comfortably
38 tok/s
ⓘ estimated
25/48GB
Runs comfortably
30 tok/s
ⓘ estimated
37/48GB
Runs comfortably
41 tok/s
ⓘ estimated
20/48GB
Runs comfortably
9 tok/s
ⓘ estimated
16/48GB
Runs comfortably
5 tok/s
ⓘ estimated
28/48GB
17.6GB
52k cap
Runs comfortably
8
tok/s
ⓘ estimated
18
/ 48GB
88
/
89
/
85
Runs comfortably
8 tok/s
ⓘ estimated
18/48GB
9.8GB
67k cap
Runs comfortably
14
tok/s
ⓘ estimated
10
/ 48GB
88
/
89
/
85
Runs comfortably
14 tok/s
ⓘ estimated
10/48GB
6.2GB
72k cap
Runs comfortably
19
tok/s
ⓘ estimated
6
/ 48GB
88
/
89
/
85
Runs comfortably
19 tok/s
ⓘ estimated
6/48GB
15.2GB
54k cap
Runs comfortably
9
tok/s
ⓘ estimated
15
/ 48GB
88
/
89
/
85
Runs comfortably
9 tok/s
ⓘ estimated
15/48GB
Runs comfortably
8 tok/s
ⓘ estimated
18/48GB
Runs comfortably
9 tok/s
ⓘ estimated
16/48GB
Runs comfortably
5 tok/s
ⓘ estimated
33/48GB
Runs comfortably
8 tok/s
ⓘ estimated
18/48GB
Runs comfortably
25 tok/s
ⓘ estimated
25/48GB
Runs comfortably
34 tok/s
ⓘ estimated
13/48GB
Runs comfortably
33 tok/s
ⓘ estimated
14/48GB
Runs comfortably
8 tok/s
ⓘ estimated
17/48GB
Runs comfortably
5 tok/s
ⓘ estimated
28/48GB
Runs comfortably
7 tok/s
ⓘ estimated
20/48GB
Runs comfortably
6 tok/s
ⓘ estimated
25/48GB
Runs comfortably
5 tok/s
ⓘ estimated
29/48GB
Runs comfortably
4 tok/s
ⓘ estimated
34/48GB
Runs comfortably
17 tok/s
ⓘ estimated
8/48GB
Nemotron 3.5 Lightning
Q4_K_M
32.0GB
31k cap
Runs comfortably
30
tok/s
ⓘ estimated
32
/ 48GB
78
/
76
/
74
Runs comfortably
30 tok/s
ⓘ estimated
32/48GB
Runs comfortably
14 tok/s
ⓘ estimated
10/48GB
Runs comfortably
8 tok/s
ⓘ estimated
18/48GB
Runs comfortably
21 tok/s
ⓘ estimated
6/48GB
Runs comfortably
19 tok/s
ⓘ estimated
7/48GB
Runs comfortably
31 tok/s
ⓘ estimated
31/48GB
Runs comfortably
43 tok/s
ⓘ estimated
16/48GB
Runs comfortably
10 tok/s
ⓘ estimated
15/48GB
Runs comfortably
5 tok/s
ⓘ estimated
29/48GB
Runs comfortably
16 tok/s
ⓘ estimated
9/48GB
Runs comfortably
21 tok/s
ⓘ estimated
20/48GB
Llama 3.3 70B Instruct
Q4_K_M
42.0GB
4k cap
Runs comfortably
3
tok/s
ⓘ estimated
42
/ 48GB
72
/
77
/
80
Runs comfortably
3 tok/s
ⓘ estimated
42/48GB
Llama 3.3 70B Instruct
Q3_K_M
30.0GB
12k cap
Runs comfortably
5
tok/s
ⓘ estimated
30
/ 48GB
72
/
77
/
80
Runs comfortably
5 tok/s
ⓘ estimated
30/48GB
21.5GB
17k cap
Runs comfortably
6
tok/s
ⓘ estimated
22
/ 48GB
72
/
77
/
80
Runs comfortably
6 tok/s
ⓘ estimated
22/48GB
Runs comfortably
15 tok/s
ⓘ estimated
9/48GB
Runs comfortably
10 tok/s
ⓘ estimated
15/48GB
Runs comfortably
18 tok/s
ⓘ estimated
7/48GB
Runs comfortably
11 tok/s
ⓘ estimated
13/48GB
Runs comfortably
5 tok/s
ⓘ estimated
28/48GB
Runs comfortably
8 tok/s
ⓘ estimated
17/48GB
Runs comfortably
23 tok/s
ⓘ estimated
5/48GB
Runs comfortably
16 tok/s
ⓘ estimated
9/48GB
Runs comfortably
18 tok/s
ⓘ estimated
8/48GB
Runs comfortably
11 tok/s
ⓘ estimated
14/48GB
Mixtral 8x7B Instruct
Q3_K_M
19.0GB
32k ctx
Runs comfortably
22
tok/s
ⓘ estimated
19
/ 48GB
62
/
65
/
68
Runs comfortably
22 tok/s
ⓘ estimated
19/48GB
Mixtral 8x7B Instruct
Q4_K_M
26.5GB
32k ctx
Runs comfortably
17
tok/s
ⓘ estimated
27
/ 48GB
62
/
65
/
68
Runs comfortably
17 tok/s
ⓘ estimated
27/48GB
Runs comfortably
18 tok/s
ⓘ estimated
7/48GB
Runs comfortably
11 tok/s
ⓘ estimated
13/48GB
Runs comfortably
44 tok/s
ⓘ estimated
3/48GB
Runs comfortably
49 tok/s
ⓘ estimated
3/48GB
Runs comfortably
33 tok/s
ⓘ estimated
4/48GB
16.0GB
64k cap
Runs comfortably
9
tok/s
ⓘ estimated
16
/ 48GB
52
/
55
/
62
Runs comfortably
9 tok/s
ⓘ estimated
16/48GB
8.0GB
80k cap
Runs comfortably
16
tok/s
ⓘ estimated
8
/ 48GB
52
/
55
/
62
Runs comfortably
16 tok/s
ⓘ estimated
8/48GB
Llama 3.1 8B Instruct
Q4_K_M
4.5GB
87k cap
Runs comfortably
25
tok/s
ⓘ estimated
5
/ 48GB
52
/
55
/
62
Runs comfortably
25 tok/s
ⓘ estimated
5/48GB
Runs comfortably
26 tok/s
ⓘ estimated
5/48GB
Runs comfortably
39 tok/s
ⓘ estimated
3/48GB
3.5GB
128k ctx
Runs comfortably
37
tok/s
ⓘ estimated
4
/ 48GB
35
/
38
/
50
Runs comfortably
37 tok/s
ⓘ estimated
4/48GB
Llama 3.2 3B Instruct
Q4_K_M
2.0GB
128k ctx
Runs comfortably
55
tok/s
ⓘ estimated
2
/ 48GB
35
/
38
/
50
Runs comfortably
55 tok/s
ⓘ estimated
2/48GB
Runs comfortably
98 tok/s
ⓘ estimated
7/48GB
Runs comfortably
31 tok/s
ⓘ estimated
24/48GB
Runs comfortably
5 tok/s
ⓘ estimated
33/48GB
Runs comfortably
8 tok/s
ⓘ estimated
18/48GB
Runs comfortably
71 tok/s
ⓘ estimated
24/48GB
Runs comfortably
112 tok/s
ⓘ estimated
14/48GB
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
GitHub Copilot
Individual
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$10.0
GitHub Copilot
Business
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$19.0
Cursor
Pro
AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...
$20.0
GitHub Copilot
Enterprise
AI coding assistant by GitHub. GPT-4o and Claude-based completions. $19/seat ...
$39.0
Cursor
Business
AI-first code editor. Uses frontier models (GPT-4, Claude). $20/user Business...
$40.0
Per-token monthly figures are estimates at typical usage. Prices verified periodically - always confirm current pricing on the provider's website.
Sign in with GitHub to save this rig and get weekly model updates
Sign in with GitHubTokenstead community
Not sure this is the right fit?
Post your rig and the shortlist in the community and get a sanity check from people running the same memory and stack.