FitMyLLM
AMD/ RDNA 4.0

AMD Radeon AI PRO R9700

32 GB
VRAM (High-end)
645 GB/s
Memory Bandwidth
236 / 290
Models fit at Q4 (81%)
~82 tok/s
7B Q4 speed (Blazing)
Model coverage at Q481% of all models

Specifications

VRAM
32 GB
Bandwidth
645 GB/s
FP16 Compute
95.7 TFLOPS
TDP
300W
Memory
GDDR6
Architecture
RDNA 4.0
Stream Processors
4,096
Compute Units
64
PCIe
Gen 5 x16
194
Fast models (>30 tok/s)
Real-time chat speed
236
Usable models (>10 tok/s)
Comfortable for all tasks
236
Total compatible
Fit in VRAM at Q4

Compatible Models(236)

S
GPT-2 124M0.124B
gpt21K ctxchat
4624
tok/s
1% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
4247
tok/s
1% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
4185
tok/s
1% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
1711
tok/s
1% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
1711
tok/s
1% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
1662
tok/s
2% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
1593
tok/s
2% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
1147
tok/s
2% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
1147
tok/s
2% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
1009
tok/s
2% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
956
tok/s
2% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
741
tok/s
2% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
717
tok/s
3% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
637
tok/s
3% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
573
tok/s
3% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
573
tok/s
3% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
521
tok/s
3% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
521
tok/s
3% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
478
tok/s
4% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
478
tok/s
2% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
441
tok/s
4% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
441
tok/s
4% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
441
tok/s
4% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
441
tok/s
4% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
382
tok/s
4% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
382
tok/s
4% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
382
tok/s
4% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
382
tok/s
4% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
382
tok/s
4% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
358
tok/s
4% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
337
tok/s
4% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
335
tok/s
4% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
319
tok/s
5% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
302
tok/s
4% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
287
tok/s
14% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
287
tok/s
5% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
287
tok/s
5% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
287
tok/s
5% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
259
tok/s
5% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
249
tok/s
6% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon AI PRO R9700.

Find Models for Radeon AI PRO R9700Compare with other GPUs