NVIDIA/ Maxwell
NVIDIA GeForce 840A
2 GB
VRAM (Budget)
16 GB/s
Memory Bandwidth
39 / 290
Models fit at Q4 (13%)
~2 tok/s
7B Q4 speed (Slow)
Model coverage at Q413% of all models
Specifications
VRAM
2 GB
Bandwidth
16 GB/s
FP16 Compute
0.9 TFLOPS
TDP
33W
Memory
DDR3
Architecture
Maxwell
CUDA Cores
384
PCIe
Gen 3 x8
7
Fast models (>30 tok/s)
Real-time chat speed
24
Usable models (>10 tok/s)
Comfortable for all tasks
39
Total compatible
Fit in VRAM at Q4
Compatible Models(39)
S
GPT-2 124M0.124B
gpt21K ctxchat
6.5
quality
VRAM18%
0.4 GB
103
tok/s
103
tok/s
18% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
7
quality
VRAM18%
0.4 GB
95
tok/s
95
tok/s
18% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
VRAM14%
0.3 GB
93
tok/s
93
tok/s
14% VRAM
B
mxbai-embed-large-v10.335B
embedding1K ctxembedding
VRAM22%
0.4 GB
38
tok/s
38
tok/s
22% VRAM
B
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
VRAM22%
0.4 GB
38
tok/s
38
tok/s
22% VRAM
B
GPT-2 Medium 345M0.345B
gpt21K ctxchat
5.9
quality
VRAM24%
0.5 GB
37
tok/s
37
tok/s
24% VRAM
B
SmolLM2 360M0.36B
smollm8K ctxchat
8.2
quality
VRAM25%
0.5 GB
36
tok/s
36
tok/s
25% VRAM
B
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
9.9
quality
VRAM38%
0.8 GB
26
tok/s
26
tok/s
38% VRAM
B
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
19.4
quality
VRAM38%
0.8 GB
26
tok/s
26
tok/s
38% VRAM
C
BGE-M30.568B
embedding8K ctxembedding
VRAM30%
0.6 GB
23
tok/s
23
tok/s
30% VRAM
C
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
20.2
quality
VRAM32%
0.6 GB
21
tok/s
21
tok/s
32% VRAM
C
GPT-2 Large 774M0.774B
gpt21K ctxchat
5.6
quality
VRAM36%
0.7 GB
17
tok/s
17
tok/s
36% VRAM
C
Qwen3-0.6B0.8B
qwen40K ctxchat
12.3
quality
VRAM47%
0.9 GB
16
tok/s
16
tok/s
47% VRAM
D
Qwen3.5-0.8B0.9B
qwen256K ctxchat
20.5
quality
VRAM50%
1.0 GB
14
tok/s
14
tok/s
50% VRAM
D
Falcon3-1B1B
falcon32K ctxchat
42
quality
VRAM50%
1.0 GB
13
tok/s
13
tok/s
50% VRAM
D
InternLM2 1B1B
internlm32K ctxchat
VRAM50%
1.0 GB
13
tok/s
13
tok/s
50% VRAM
D
TinyLlama-1.1B1.1B
llama2K ctxchat
13.6
quality
VRAM55%
1.1 GB
12
tok/s
12
tok/s
55% VRAM
D
TinyLlama 1.1B1.1B
llama2K ctxchat
13.6
quality
VRAM55%
1.1 GB
12
tok/s
12
tok/s
55% VRAM
D
Llama-3.2-1B1.2B
llama4K ctxchat
13.6
quality
VRAM58%
1.2 GB
11
tok/s
11
tok/s
58% VRAM
D
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
18.3
quality
VRAM36%
0.7 GB
11
tok/s
11
tok/s
36% VRAM
D
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
16.8
quality
VRAM61%
1.2 GB
10
tok/s
10
tok/s
61% VRAM
D
OPT 1.3B1.3B
opt2K ctxchat
5.3
quality
VRAM59%
1.2 GB
10
tok/s
10
tok/s
59% VRAM
D
Phi-1 1.3B1.3B
phi2K ctxcoding
7.2
quality
VRAM61%
1.2 GB
10
tok/s
10
tok/s
61% VRAM
D
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
7.2
quality
VRAM61%
1.2 GB
10
tok/s
10
tok/s
61% VRAM
D
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
5.1
quality
VRAM64%
1.3 GB
9
tok/s
9
tok/s
64% VRAM
D
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
22.8
quality
VRAM67%
1.3 GB
9
tok/s
9
tok/s
67% VRAM
D
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
22.8
quality
VRAM67%
1.3 GB
9
tok/s
9
tok/s
67% VRAM
D
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
30.2
quality
VRAM67%
1.3 GB
9
tok/s
9
tok/s
67% VRAM
D
Yi Coder 1.5B1.5B
yi125K ctxcoding
14.6
quality
VRAM67%
1.3 GB
9
tok/s
9
tok/s
67% VRAM
D
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
32.6
quality
VRAM70%
1.4 GB
8
tok/s
8
tok/s
70% VRAM
D
stablelm-2-1_6b1.6B
stablelm4K ctxchat
9.5
quality
VRAM69%
1.4 GB
8
tok/s
8
tok/s
69% VRAM
F
Moondream2 1.9B1.9B
other2K ctxvisionchat
26.2
quality
VRAM68%
1.4 GB
7
tok/s
7
tok/s
68% VRAM
F
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
22.8
quality
VRAM75%
1.5 GB
7
tok/s
7
tok/s
75% VRAM
F
SmolLM2 1.7B1.71B
smollm8K ctxchat
16.2
quality
VRAM70%
1.4 GB
7
tok/s
7
tok/s
70% VRAM
F
Qwen3.5-2B2.3B
qwen256K ctxchat
15.9
quality
VRAM89%
1.8 GB
6
tok/s
6
tok/s
89% VRAM
F
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
28.3
quality
VRAM84%
1.7 GB
6
tok/s
6
tok/s
84% VRAM
F
Gemma 1 2B2B
gemma8K ctxchat
20.2
quality
VRAM81%
1.6 GB
6
tok/s
6
tok/s
81% VRAM
F
Granite 3.0 2B2B
granite128K ctxchatcoding
35.8
quality
VRAM78%
1.6 GB
6
tok/s
6
tok/s
78% VRAM
F
Granite 3.1 2B2B
granite128K ctxchatcoding
37.8
quality
VRAM78%
1.6 GB
6
tok/s
6
tok/s
78% VRAM
Get personalized recommendations
See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce 840A.