FitMyLLM
AMD/ GCN 5.0

AMD Atari VCS 400 GPU

4 GB
VRAM (Budget)
38 GB/s
Memory Bandwidth
64 / 290
Models fit at Q4 (22%)
~5 tok/s
7B Q4 speed (Slow)
Model coverage at Q422% of all models

Specifications

VRAM
4 GB
Bandwidth
38 GB/s
FP16 Compute
0.9 TFLOPS
TDP
15W
Memory
DDR4
Architecture
GCN 5.0
Stream Processors
192
Compute Units
3
18
Fast models (>30 tok/s)
Real-time chat speed
52
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
272
tok/s
9% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
250
tok/s
9% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
247
tok/s
7% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
101
tok/s
11% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
101
tok/s
11% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
98
tok/s
12% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
94
tok/s
12% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
68
tok/s
19% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
68
tok/s
19% VRAM
A
BGE-M30.568B
embedding8K ctxembedding
59
tok/s
15% VRAM
A
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
56
tok/s
16% VRAM
A
GPT-2 Large 774M0.774B
gpt21K ctxchat
44
tok/s
18% VRAM
A
Qwen3-0.6B0.8B
qwen40K ctxchat
42
tok/s
23% VRAM
B
Qwen3.5-0.8B0.9B
qwen256K ctxchat
38
tok/s
25% VRAM
B
Falcon3-1B1B
falcon32K ctxchat
34
tok/s
25% VRAM
B
InternLM2 1B1B
internlm32K ctxchat
34
tok/s
25% VRAM
B
TinyLlama-1.1B1.1B
llama2K ctxchat
31
tok/s
28% VRAM
B
TinyLlama 1.1B1.1B
llama2K ctxchat
31
tok/s
28% VRAM
B
Llama-3.2-1B1.2B
llama4K ctxchat
28
tok/s
29% VRAM
B
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
28
tok/s
18% VRAM
B
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
26
tok/s
30% VRAM
B
OPT 1.3B1.3B
opt2K ctxchat
26
tok/s
29% VRAM
B
Phi-1 1.3B1.3B
phi2K ctxcoding
26
tok/s
30% VRAM
B
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
26
tok/s
30% VRAM
C
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
23
tok/s
32% VRAM
C
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
23
tok/s
33% VRAM
C
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
23
tok/s
33% VRAM
C
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
23
tok/s
33% VRAM
C
Yi Coder 1.5B1.5B
yi125K ctxcoding
23
tok/s
33% VRAM
C
stablelm-2-1_6b1.6B
stablelm4K ctxchat
21
tok/s
35% VRAM
C
SmolLM2 1.7B1.71B
smollm8K ctxchat
20
tok/s
35% VRAM
C
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
20
tok/s
35% VRAM
C
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
19
tok/s
38% VRAM
C
Moondream2 1.9B1.9B
other2K ctxvisionchat
18
tok/s
34% VRAM
C
Gemma 1 2B2B
gemma8K ctxchat
17
tok/s
40% VRAM
C
Granite 3.0 2B2B
granite128K ctxchatcoding
17
tok/s
39% VRAM
C
Granite 3.1 2B2B
granite128K ctxchatcoding
17
tok/s
39% VRAM
C
Qwen3.5-2B2.3B
qwen256K ctxchat
15
tok/s
45% VRAM
C
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
15
tok/s
42% VRAM
D
OPT 2.7B2.7B
opt2K ctxchat
13
tok/s
49% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Atari VCS 400 GPU.

Find Models for Atari VCS 400 GPUCompare with other GPUs