FitMyLLM
AMD/ GCN 3.0

AMD Radeon R7 M445

4 GB
VRAM (Budget)
32 GB/s
Memory Bandwidth
64 / 290
Models fit at Q4 (22%)
~4 tok/s
7B Q4 speed (Slow)
Model coverage at Q422% of all models

Specifications

VRAM
4 GB
Bandwidth
32 GB/s
FP16 Compute
0.6 TFLOPS
Memory
GDDR5
Architecture
GCN 3.0
Stream Processors
320
Compute Units
5
PCIe
Gen 3 x8
14
Fast models (>30 tok/s)
Real-time chat speed
46
Usable models (>10 tok/s)
Comfortable for all tasks
64
Total compatible
Fit in VRAM at Q4

Compatible Models(64)

S
GPT-2 124M0.124B
gpt21K ctxchat
229
tok/s
9% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
211
tok/s
9% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
208
tok/s
7% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
85
tok/s
11% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
85
tok/s
11% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
82
tok/s
12% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
79
tok/s
12% VRAM
A
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
57
tok/s
19% VRAM
A
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
57
tok/s
19% VRAM
A
BGE-M30.568B
embedding8K ctxembedding
50
tok/s
15% VRAM
A
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
47
tok/s
16% VRAM
B
GPT-2 Large 774M0.774B
gpt21K ctxchat
37
tok/s
18% VRAM
B
Qwen3-0.6B0.8B
qwen40K ctxchat
36
tok/s
23% VRAM
B
Qwen3.5-0.8B0.9B
qwen256K ctxchat
32
tok/s
25% VRAM
B
Falcon3-1B1B
falcon32K ctxchat
28
tok/s
25% VRAM
B
InternLM2 1B1B
internlm32K ctxchat
28
tok/s
25% VRAM
B
TinyLlama-1.1B1.1B
llama2K ctxchat
26
tok/s
28% VRAM
B
TinyLlama 1.1B1.1B
llama2K ctxchat
26
tok/s
28% VRAM
C
Llama-3.2-1B1.2B
llama4K ctxchat
24
tok/s
29% VRAM
C
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
24
tok/s
18% VRAM
C
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
22
tok/s
30% VRAM
C
OPT 1.3B1.3B
opt2K ctxchat
22
tok/s
29% VRAM
C
Phi-1 1.3B1.3B
phi2K ctxcoding
22
tok/s
30% VRAM
C
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
22
tok/s
30% VRAM
C
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
19
tok/s
32% VRAM
C
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
19
tok/s
33% VRAM
C
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
19
tok/s
33% VRAM
C
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
19
tok/s
33% VRAM
C
Yi Coder 1.5B1.5B
yi125K ctxcoding
19
tok/s
33% VRAM
C
stablelm-2-1_6b1.6B
stablelm4K ctxchat
18
tok/s
35% VRAM
C
SmolLM2 1.7B1.71B
smollm8K ctxchat
17
tok/s
35% VRAM
C
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
17
tok/s
35% VRAM
C
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
16
tok/s
38% VRAM
C
Moondream2 1.9B1.9B
other2K ctxvisionchat
15
tok/s
34% VRAM
D
Gemma 1 2B2B
gemma8K ctxchat
14
tok/s
40% VRAM
D
Granite 3.0 2B2B
granite128K ctxchatcoding
14
tok/s
39% VRAM
D
Granite 3.1 2B2B
granite128K ctxchatcoding
14
tok/s
39% VRAM
D
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
13
tok/s
42% VRAM
D
Qwen3.5-2B2.3B
qwen256K ctxchat
12
tok/s
45% VRAM
D
OPT 2.7B2.7B
opt2K ctxchat
11
tok/s
49% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon R7 M445.

Find Models for Radeon R7 M445Compare with other GPUs