FitMyLLM
AMD/ RDNA 2.0

AMD Ryzen Z2 Go GPU

16 GB
VRAM (Mid-range)
102 GB/s
Memory Bandwidth
191 / 290
Models fit at Q4 (66%)
~13 tok/s
7B Q4 speed (Usable)
Model coverage at Q466% of all models

Specifications

VRAM
16 GB
Bandwidth
102 GB/s
FP16 Compute
8.3 TFLOPS
TDP
28W
Memory
LPDDR5
Architecture
RDNA 2.0
Stream Processors
768
Compute Units
12
53
Fast models (>30 tok/s)
Real-time chat speed
145
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
731
tok/s
2% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
672
tok/s
2% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
662
tok/s
2% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
271
tok/s
3% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
271
tok/s
3% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
263
tok/s
3% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
252
tok/s
3% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
181
tok/s
5% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
181
tok/s
5% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
160
tok/s
4% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
151
tok/s
4% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
117
tok/s
5% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
113
tok/s
6% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
101
tok/s
6% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
91
tok/s
6% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
91
tok/s
6% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
82
tok/s
7% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
82
tok/s
7% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
76
tok/s
7% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
76
tok/s
4% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
70
tok/s
8% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
70
tok/s
7% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
70
tok/s
8% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
70
tok/s
8% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
60
tok/s
8% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
60
tok/s
8% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
60
tok/s
8% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
60
tok/s
8% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
60
tok/s
8% VRAM
A
stablelm-2-1_6b1.6B
stablelm4K ctxchat
57
tok/s
9% VRAM
A
SmolLM2 1.7B1.71B
smollm8K ctxchat
53
tok/s
9% VRAM
A
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
53
tok/s
9% VRAM
A
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
50
tok/s
9% VRAM
A
Moondream2 1.9B1.9B
other2K ctxvisionchat
48
tok/s
9% VRAM
A
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
45
tok/s
28% VRAM
A
Gemma 1 2B2B
gemma8K ctxchat
45
tok/s
10% VRAM
A
Granite 3.0 2B2B
granite128K ctxchatcoding
45
tok/s
10% VRAM
A
Granite 3.1 2B2B
granite128K ctxchatcoding
45
tok/s
10% VRAM
A
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
41
tok/s
11% VRAM
B
Qwen3.5-2B2.3B
qwen256K ctxchat
39
tok/s
11% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Ryzen Z2 Go GPU.

Find Models for Ryzen Z2 Go GPUCompare with other GPUs