FitMyLLM
AMD/ CDNA 2.0

AMD Radeon Instinct MI250X

128 GB
VRAM (Flagship)
3280 GB/s
Memory Bandwidth
274 / 290
Models fit at Q4 (94%)
~417 tok/s
7B Q4 speed (Blazing)
Model coverage at Q494% of all models

Specifications

VRAM
128 GB
Bandwidth
3280 GB/s
FP16 Compute
383 TFLOPS
TDP
500W
Memory
HBM2e
Architecture
CDNA 2.0
Stream Processors
14,080
Compute Units
110
PCIe
Gen 4 x16
265
Fast models (>30 tok/s)
Real-time chat speed
274
Usable models (>10 tok/s)
Comfortable for all tasks
274
Total compatible
Fit in VRAM at Q4

Compatible Models(274)

S
GPT-2 124M0.124B
gpt21K ctxchat
23513
tok/s
0% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
21597
tok/s
0% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
21281
tok/s
0% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
8703
tok/s
0% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
8703
tok/s
0% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
8451
tok/s
0% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
8099
tok/s
0% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
5831
tok/s
1% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
5831
tok/s
1% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
5133
tok/s
0% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
4859
tok/s
0% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
3767
tok/s
1% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
3644
tok/s
1% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
3240
tok/s
1% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
2916
tok/s
1% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
2916
tok/s
1% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
2651
tok/s
1% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
2651
tok/s
1% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
2430
tok/s
1% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
2430
tok/s
1% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
2243
tok/s
1% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
2243
tok/s
1% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
2243
tok/s
1% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
2243
tok/s
1% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
1944
tok/s
1% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
1944
tok/s
1% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
1944
tok/s
1% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
1944
tok/s
1% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
1944
tok/s
1% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
1822
tok/s
1% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
1715
tok/s
1% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
1705
tok/s
1% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
1620
tok/s
1% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
1535
tok/s
1% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
1458
tok/s
3% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
1458
tok/s
1% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
1458
tok/s
1% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
1458
tok/s
1% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
1319
tok/s
1% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
1268
tok/s
1% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon Instinct MI250X.

Find Models for Radeon Instinct MI250XCompare with other GPUs