FitMyLLM
AMD/ GCN 2.0

AMD Radeon R9 M380 Mac Edition

2 GB
VRAM (Budget)
100 GB/s
Memory Bandwidth
39 / 290
Models fit at Q4 (13%)
~13 tok/s
7B Q4 speed (Usable)
Model coverage at Q413% of all models

Specifications

VRAM
2 GB
Bandwidth
100 GB/s
FP16 Compute
1.6 TFLOPS
Memory
GDDR5
Architecture
GCN 2.0
Stream Processors
768
Compute Units
12
PCIe
Gen 3 x16
39
Fast models (>30 tok/s)
Real-time chat speed
39
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
717
tok/s
18% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
658
tok/s
18% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
649
tok/s
14% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
265
tok/s
22% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
265
tok/s
22% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
258
tok/s
24% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
247
tok/s
25% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
178
tok/s
38% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
178
tok/s
38% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
156
tok/s
30% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
148
tok/s
32% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
115
tok/s
36% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
111
tok/s
47% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
99
tok/s
50% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
89
tok/s
50% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
89
tok/s
50% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
81
tok/s
55% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
81
tok/s
55% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
74
tok/s
58% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
74
tok/s
36% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
68
tok/s
61% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
68
tok/s
59% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
68
tok/s
61% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
68
tok/s
61% VRAM
A
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
59
tok/s
64% VRAM
A
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
59
tok/s
67% VRAM
A
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
59
tok/s
67% VRAM
A
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
59
tok/s
67% VRAM
A
Yi Coder 1.5B1.5B
yi125K ctxcoding
59
tok/s
67% VRAM
A
stablelm-2-1_6b1.6B
stablelm4K ctxchat
56
tok/s
69% VRAM
A
SmolLM2 1.7B1.71B
smollm8K ctxchat
52
tok/s
70% VRAM
A
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
52
tok/s
70% VRAM
A
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
49
tok/s
75% VRAM
A
Moondream2 1.9B1.9B
other2K ctxvisionchat
47
tok/s
68% VRAM
A
Gemma 1 2B2B
gemma8K ctxchat
44
tok/s
81% VRAM
A
Granite 3.0 2B2B
granite128K ctxchatcoding
44
tok/s
78% VRAM
A
Granite 3.1 2B2B
granite128K ctxchatcoding
44
tok/s
78% VRAM
A
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
40
tok/s
84% VRAM
B
Qwen3.5-2B2.3B
qwen256K ctxchat
39
tok/s
89% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon R9 M380 Mac Edition.

Find Models for Radeon R9 M380 Mac EditionCompare with other GPUs