FitMyLLM
AMD/ RDNA 3.0

AMD Ryzen Z1 Extreme GPU

16 GB
VRAM (Mid-range)
51 GB/s
Memory Bandwidth
191 / 290
Models fit at Q4 (66%)
~6 tok/s
7B Q4 speed (Slow)
Model coverage at Q466% of all models

Specifications

VRAM
16 GB
Bandwidth
51 GB/s
FP16 Compute
16.6 TFLOPS
TDP
30W
Memory
LPDDR5
Architecture
RDNA 3.0
Stream Processors
768
Compute Units
12
29
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
366
tok/s
2% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
336
tok/s
2% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
331
tok/s
2% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
135
tok/s
3% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
135
tok/s
3% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
131
tok/s
3% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
126
tok/s
3% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
91
tok/s
5% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
91
tok/s
5% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
80
tok/s
4% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
76
tok/s
4% VRAM
A
GPT-2 Large 774M0.774B
gpt21K ctxchat
59
tok/s
5% VRAM
A
Qwen3-0.6B0.8B
qwen40K ctxchat
57
tok/s
6% VRAM
A
Qwen3.5-0.8B0.9B
qwen256K ctxchat
50
tok/s
6% VRAM
A
Falcon3-1B1B
falcon32K ctxchat
45
tok/s
6% VRAM
A
InternLM2 1B1B
internlm32K ctxchat
45
tok/s
6% VRAM
A
TinyLlama-1.1B1.1B
llama2K ctxchat
41
tok/s
7% VRAM
A
TinyLlama 1.1B1.1B
llama2K ctxchat
41
tok/s
7% VRAM
B
Llama-3.2-1B1.2B
llama4K ctxchat
38
tok/s
7% VRAM
B
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
38
tok/s
4% VRAM
B
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
35
tok/s
8% VRAM
B
OPT 1.3B1.3B
opt2K ctxchat
35
tok/s
7% VRAM
B
Phi-1 1.3B1.3B
phi2K ctxcoding
35
tok/s
8% VRAM
B
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
35
tok/s
8% VRAM
B
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
30
tok/s
8% VRAM
B
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
30
tok/s
8% VRAM
B
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
30
tok/s
8% VRAM
B
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
30
tok/s
8% VRAM
B
Yi Coder 1.5B1.5B
yi125K ctxcoding
30
tok/s
8% VRAM
B
stablelm-2-1_6b1.6B
stablelm4K ctxchat
28
tok/s
9% VRAM
B
SmolLM2 1.7B1.71B
smollm8K ctxchat
27
tok/s
9% VRAM
B
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
27
tok/s
9% VRAM
B
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
25
tok/s
9% VRAM
C
Moondream2 1.9B1.9B
other2K ctxvisionchat
24
tok/s
9% VRAM
C
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
23
tok/s
28% VRAM
C
Gemma 1 2B2B
gemma8K ctxchat
23
tok/s
10% VRAM
C
Granite 3.0 2B2B
granite128K ctxchatcoding
23
tok/s
10% VRAM
C
Granite 3.1 2B2B
granite128K ctxchatcoding
23
tok/s
10% VRAM
C
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
21
tok/s
11% VRAM
C
Qwen3.5-2B2.3B
qwen256K ctxchat
20
tok/s
11% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Ryzen Z1 Extreme GPU.

Find Models for Ryzen Z1 Extreme GPUCompare with other GPUs