Model
Fit
Speed
Memory
Scores / Run
Runs comfortably
Runs comfortably
21 tok/s
ⓘ estimated
38/64GB
Ornith-1.5-35B-A3B
Q4_K_M
21.7GB
76k cap
Runs comfortably
28
tok/s
ⓘ estimated
22
/ 64GB
91
/
89
/
86
Runs comfortably
28 tok/s
ⓘ estimated
22/64GB
Runs comfortably
24 tok/s
ⓘ estimated
29/64GB
Ornith-1.5-35B-A3B
Q5_K_M
25.3GB
69k cap
Runs comfortably
26
tok/s
ⓘ estimated
25
/ 64GB
91
/
89
/
86
Runs comfortably
26 tok/s
ⓘ estimated
25/64GB
Runs comfortably
28 tok/s
ⓘ estimated
20/64GB
Runs comfortably
21 tok/s
ⓘ estimated
37/64GB
Runs comfortably
4 tok/s
ⓘ estimated
28/64GB
Runs comfortably
2 tok/s
ⓘ estimated
56/64GB
Runs comfortably
6 tok/s
ⓘ estimated
16/64GB
17.6GB
81k cap
Runs comfortably
6
tok/s
ⓘ estimated
18
/ 64GB
88
/
89
/
85
Runs comfortably
6 tok/s
ⓘ estimated
18/64GB
9.8GB
96k cap
Runs comfortably
9
tok/s
ⓘ estimated
10
/ 64GB
88
/
89
/
85
Runs comfortably
9 tok/s
ⓘ estimated
10/64GB
6.2GB
101k cap
Runs comfortably
13
tok/s
ⓘ estimated
6
/ 64GB
88
/
89
/
85
Runs comfortably
13 tok/s
ⓘ estimated
6/64GB
Runs comfortably
3 tok/s
ⓘ estimated
33/64GB
Runs comfortably
5 tok/s
ⓘ estimated
18/64GB
Runs comfortably
5 tok/s
ⓘ estimated
18/64GB
Runs comfortably
11 tok/s
ⓘ estimated
50/64GB
Runs comfortably
17 tok/s
ⓘ estimated
25/64GB
Runs comfortably
23 tok/s
ⓘ estimated
13/64GB
Runs comfortably
4 tok/s
ⓘ estimated
28/64GB
Runs comfortably
6 tok/s
ⓘ estimated
17/64GB
Runs comfortably
5 tok/s
ⓘ estimated
20/64GB
Runs comfortably
4 tok/s
ⓘ estimated
25/64GB
Runs comfortably
4 tok/s
ⓘ estimated
29/64GB
Runs comfortably
3 tok/s
ⓘ estimated
34/64GB
Runs comfortably
12 tok/s
ⓘ estimated
8/64GB
Nemotron 3.5 Lightning
Q4_K_M
32.0GB
66k cap
Runs comfortably
21
tok/s
ⓘ estimated
32
/ 64GB
78
/
76
/
74
Runs comfortably
21 tok/s
ⓘ estimated
32/64GB
Runs comfortably
10 tok/s
ⓘ estimated
10/64GB
Runs comfortably
6 tok/s
ⓘ estimated
18/64GB
Runs comfortably
14 tok/s
ⓘ estimated
6/64GB
Runs comfortably
13 tok/s
ⓘ estimated
7/64GB
Runs comfortably
30 tok/s
ⓘ estimated
16/64GB
Runs comfortably
21 tok/s
ⓘ estimated
31/64GB
Runs comfortably
11 tok/s
ⓘ estimated
9/64GB
Runs comfortably
7 tok/s
ⓘ estimated
15/64GB
Runs comfortably
4 tok/s
ⓘ estimated
29/64GB
Runs comfortably
15 tok/s
ⓘ estimated
20/64GB
Llama 3.3 70B Instruct
Q3_K_M
30.0GB
22k cap
Runs comfortably
3
tok/s
ⓘ estimated
30
/ 64GB
72
/
77
/
80
Runs comfortably
3 tok/s
ⓘ estimated
30/64GB
21.5GB
28k cap
Runs comfortably
4
tok/s
ⓘ estimated
22
/ 64GB
72
/
77
/
80
Runs comfortably
4 tok/s
ⓘ estimated
22/64GB
Llama 3.3 70B Instruct
Q4_K_M
42.0GB
14k cap
Runs comfortably
2
tok/s
ⓘ estimated
42
/ 64GB
72
/
77
/
80
Runs comfortably
2 tok/s
ⓘ estimated
42/64GB
Runs comfortably
10 tok/s
ⓘ estimated
9/64GB
Runs comfortably
7 tok/s
ⓘ estimated
15/64GB
Runs comfortably
12 tok/s
ⓘ estimated
7/64GB
Runs comfortably
8 tok/s
ⓘ estimated
13/64GB
Runs comfortably
4 tok/s
ⓘ estimated
28/64GB
Runs comfortably
6 tok/s
ⓘ estimated
17/64GB
Runs comfortably
11 tok/s
ⓘ estimated
9/64GB
Runs comfortably
16 tok/s
ⓘ estimated
5/64GB
Mixtral 8x7B Instruct
Q3_K_M
19.0GB
32k ctx
Runs comfortably
15
tok/s
ⓘ estimated
19
/ 64GB
62
/
65
/
68
Runs comfortably
15 tok/s
ⓘ estimated
19/64GB
Mixtral 8x7B Instruct
Q4_K_M
26.5GB
32k ctx
Runs comfortably
12
tok/s
ⓘ estimated
27
/ 64GB
62
/
65
/
68
Runs comfortably
12 tok/s
ⓘ estimated
27/64GB
Runs comfortably
7 tok/s
ⓘ estimated
14/64GB
Runs comfortably
12 tok/s
ⓘ estimated
8/64GB
Runs comfortably
8 tok/s
ⓘ estimated
13/64GB
Runs comfortably
13 tok/s
ⓘ estimated
7/64GB
Runs comfortably
30 tok/s
ⓘ estimated
3/64GB
Runs comfortably
23 tok/s
ⓘ estimated
4/64GB
Runs comfortably
34 tok/s
ⓘ estimated
3/64GB
8.0GB
112k cap
Runs comfortably
11
tok/s
ⓘ estimated
8
/ 64GB
52
/
55
/
62
Runs comfortably
11 tok/s
ⓘ estimated
8/64GB
Llama 3.1 8B Instruct
Q4_K_M
4.5GB
119k cap
Runs comfortably
17
tok/s
ⓘ estimated
5
/ 64GB
52
/
55
/
62
Runs comfortably
17 tok/s
ⓘ estimated
5/64GB
16.0GB
96k cap
Runs comfortably
6
tok/s
ⓘ estimated
16
/ 64GB
52
/
55
/
62
Runs comfortably
6 tok/s
ⓘ estimated
16/64GB
Runs comfortably
18 tok/s
ⓘ estimated
5/64GB
Runs comfortably
27 tok/s
ⓘ estimated
3/64GB
3.5GB
128k ctx
Runs comfortably
25
tok/s
ⓘ estimated
4
/ 64GB
35
/
38
/
50
Runs comfortably
25 tok/s
ⓘ estimated
4/64GB
Llama 3.2 3B Instruct
Q4_K_M
2.0GB
128k ctx
Runs comfortably
38
tok/s
ⓘ estimated
2
/ 64GB
35
/
38
/
50
Runs comfortably
38 tok/s
ⓘ estimated
2/64GB
Runs comfortably
68 tok/s
ⓘ estimated
7/64GB
Runs comfortably
22 tok/s
ⓘ estimated
24/64GB
Runs comfortably
3 tok/s
ⓘ estimated
33/64GB
Runs comfortably
6 tok/s
ⓘ estimated
18/64GB
Runs comfortably
49 tok/s
ⓘ estimated
24/64GB
Runs comfortably
77 tok/s
ⓘ estimated
14/64GB
Runs tight
Runs tight
30 tok/s
ⓘ estimated
63/64GB
Runs tight
2 tok/s
ⓘ estimated
61/64GB
60.0GB
ctx headroom ~0
Runs tight
13
tok/s
ⓘ estimated
60
/ 64GB
78
/
76
/
74
Runs tight
13 tok/s
ⓘ estimated
60/64GB
Runs tight
13 tok/s
ⓘ estimated
58/64GB
Runs tight
8 tok/s
ⓘ estimated
62/64GB
Runs tight
2 tok/s
ⓘ estimated
61/64GB
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.