FitMyLLM
NVIDIA/ Volta

NVIDIA Jetson Xavier NX 16 GB

16 GB
VRAM (Mid-range)
60 GB/s
Memory Bandwidth
191 / 290
Models fit at Q4 (66%)
~7 tok/s
7B Q4 speed (Slow)
Model coverage at Q466% of all models

Specifications

VRAM
16 GB
Bandwidth
60 GB/s
FP16 Compute
1.7 TFLOPS
TDP
20W
Memory
LPDDR4X
Architecture
Volta
CUDA Cores
384
Tensor Cores
48
PCIe
Gen 4 x4
30
Fast models (>30 tok/s)
Real-time chat speed
68
Usable models (>10 tok/s)
Comfortable for all tasks
191
Total compatible
Fit in VRAM at Q4

Compatible Models(191)

S
GPT-2 124M0.124B
gpt21K ctxchat
387
tok/s
2% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
356
tok/s
2% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
350
tok/s
2% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
143
tok/s
3% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
143
tok/s
3% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
139
tok/s
3% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
133
tok/s
3% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
96
tok/s
5% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
96
tok/s
5% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
85
tok/s
4% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
80
tok/s
4% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
62
tok/s
5% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
60
tok/s
6% VRAM
A
Qwen3.5-0.8B0.9B
qwen256K ctxchat
53
tok/s
6% VRAM
A
Falcon3-1B1B
falcon32K ctxchat
48
tok/s
6% VRAM
A
InternLM2 1B1B
internlm32K ctxchat
48
tok/s
6% VRAM
A
TinyLlama-1.1B1.1B
llama2K ctxchat
44
tok/s
7% VRAM
A
TinyLlama 1.1B1.1B
llama2K ctxchat
44
tok/s
7% VRAM
A
Llama-3.2-1B1.2B
llama4K ctxchat
40
tok/s
7% VRAM
A
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
40
tok/s
4% VRAM
B
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
37
tok/s
8% VRAM
B
OPT 1.3B1.3B
opt2K ctxchat
37
tok/s
7% VRAM
B
Phi-1 1.3B1.3B
phi2K ctxcoding
37
tok/s
8% VRAM
B
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
37
tok/s
8% VRAM
B
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
32
tok/s
8% VRAM
B
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
32
tok/s
8% VRAM
B
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
32
tok/s
8% VRAM
B
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
32
tok/s
8% VRAM
B
Yi Coder 1.5B1.5B
yi125K ctxcoding
32
tok/s
8% VRAM
B
stablelm-2-1_6b1.6B
stablelm4K ctxchat
30
tok/s
9% VRAM
B
SmolLM2 1.7B1.71B
smollm8K ctxchat
28
tok/s
9% VRAM
B
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
28
tok/s
9% VRAM
B
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
27
tok/s
9% VRAM
B
Moondream2 1.9B1.9B
other2K ctxvisionchat
25
tok/s
9% VRAM
C
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
24
tok/s
28% VRAM
C
Gemma 1 2B2B
gemma8K ctxchat
24
tok/s
10% VRAM
C
Granite 3.0 2B2B
granite128K ctxchatcoding
24
tok/s
10% VRAM
C
Granite 3.1 2B2B
granite128K ctxchatcoding
24
tok/s
10% VRAM
C
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
22
tok/s
11% VRAM
C
Qwen3.5-2B2.3B
qwen256K ctxchat
21
tok/s
11% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Jetson Xavier NX 16 GB.

Find Models for Jetson Xavier NX 16 GBCompare with other GPUs