FitMyLLM
▸ AMD· RDNA 4.0

AMD Radeon AI PRO R9700S

Running LLMs on the Radeon AI PRO R9700S — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
32 GB
HIGH-END
BANDWIDTH
645
GB/S
MODELS Q4
337/449
75%
7B Q4 SPEED
~82
BLAZING
▸ MODEL COVERAGE @ Q475% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~191
TOK/S
7B
~82
TOK/S
14B
~41
TOK/S
32B
~18
TOK/S
70B
—
39.4GB NEEDED
▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS →
▸ 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
278
FAST MODELS · >30 TOK/S
Real-time chat speed
337
USABLE · >10 TOK/S
Comfortable for all tasks
337
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Radeon AI PRO R9700S (or anything bigger) without committing. Pay by the second, cancel anytime.

Rent on Vast.ai →Or RunPod →

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 337
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
6370
TOK/S · 2% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
4247
TOK/S · 2% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
4095
TOK/S · 2% VRAM
›
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
4095
TOK/S · 2% VRAM
›
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
2240
TOK/S · 2% VRAM
›
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
2123
TOK/S · 2% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
1880
TOK/S · 2% VRAM
›
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
1711
TOK/S · 2% VRAM
›
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
1711
TOK/S · 2% VRAM
›
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
1711
TOK/S · 2% VRAM
›
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
1638
TOK/S · 2% VRAM
›
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
1593
TOK/S · 2% VRAM
›
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
1509
TOK/S · 2% VRAM
›
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
1147
TOK/S · 2% VRAM
›
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
1147
TOK/S · 2% VRAM
›
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
1103
TOK/S · 3% VRAM
›
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
1009
TOK/S · 3% VRAM
›
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
1009
TOK/S · 3% VRAM
›
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
956
TOK/S · 3% VRAM
›
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
956
TOK/S · 3% VRAM
›
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
956
TOK/S · 3% VRAM
›
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
925
TOK/S · 3% VRAM
›
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
775
TOK/S · 3% VRAM
›
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
764
TOK/S · 3% VRAM
›
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
708
TOK/S · 3% VRAM
›
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
659
TOK/S · 3% VRAM
›
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
610
TOK/S · 3% VRAM
›
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
531
TOK/S · 4% VRAM
›
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
521
TOK/S · 4% VRAM
›
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
478
TOK/S · 4% VRAM
›
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
478
TOK/S · 4% VRAM
›
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
478
TOK/S · 4% VRAM
›
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
478
TOK/S · 4% VRAM
›
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
441
TOK/S · 4% VRAM
›
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
441
TOK/S · 4% VRAM
›
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
441
TOK/S · 4% VRAM
›
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
425
TOK/S · 4% VRAM
›
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
404
TOK/S · 4% VRAM
›
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
404
TOK/S · 4% VRAM
›
S
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
382
TOK/S · 17% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon AI PRO R9700S.

▸Find models for Radeon AI PRO R9700SCompare with other GPUs
WHAT THIS CARD IS WORTH

Radeon AI PRO R9700S holds 337 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is Phi-3.5 MoE 42B at Q4_K_M.

TOKENS/SEC PER $100
—
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
—
what memory costs on this card
THE BIGGEST IT TAKES
Phi-3.5 MoE 42B41.9B · Q4_K_M28.6 GB78 tok/sEST
Falcon 40B40B · Q4_K_M27.4 GB18 tok/sEST
InternVL3 38B38B · Q4_K_M26.7 GB19 tok/sEST
Seed-OSS 36B Instruct36B · Q5_K_S28.6 GB17 tok/sEST
c4ai-command-r-v01 35B35B · Q5_K_M28.1 GB17 tok/sEST
Qwen 3.5 35B A3B35B · Q5_K_M27.5 GB126 tok/sEST
Qwen 3.6 35B A3B35B · Q5_K_M27.5 GB126 tok/sEST
Nous Capybara 34B34.4B · Q5_K_M27.9 GB18 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M4 Max (48GB)36 GB$2,4992.2 tok/s per $100
M3 Max (48GB)36 GB$2,8991.6 tok/s per $100
M4 Pro (48GB)36 GB$1,7991.9 tok/s per $100
A100 SXM4 40 GB40 GB$10,0001.4 tok/s per $100
Radeon AI PRO R9700S32 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

AMD Radeon AI PRO R9700S — 32 GB VRAM.

▸ RADEON AI PRO R9700S SPEC
BRAND
AMD
VRAM
32 GB GDDR6
BANDWIDTH
645 GB/s
FP16 COMPUTE
95.7 TFLOPS
FP32 COMPUTE
47.8 TFLOPS
STREAM PROCESSORS
4,096
TDP
300 W
ARCHITECTURE
RDNA 4.0
▸ AI CAPABILITY
337/ 449 models @ Q4

With 32 GB VRAM and 645 GB/s bandwidth, this GPU handles models up to 41.9B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~74 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR RADEON AI PRO R9700S
337 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Phi-3.5 MoE 42B41.9B26.1 GB8756.7
Falcon 40B40B24.9 GB1420.9
InternVL3 38B38B23.7 GB1578.9
Seed-OSS 36B Instruct36B22.5 GB1654.4
c4ai-command-r-v01 35B35B21.9 GB1627.5
Qwen 3.5 35B A3B35B21.9 GB19153.3
Qwen 3.6 35B A3B35B21.9 GB19153.9
Nous Capybara 34B34.4B21.5 GB1742.0
Yi-1.5 34B34.4B21.5 GB1745.3
Falcon-H1 34B34B21.3 GB1766.1
CodeLlama 34B34B21.3 GB1725.4
Nous Hermes 2 34B34B21.3 GB1747.0
Phind CodeLlama 34B34B21.3 GB1768.1
LLaVA-1.6 Yi 34B34B21.3 GB1747.4
WizardCoder Python 34B34B21.3 GB1773.2
Yi 34B34B21.3 GB1733.4
Qwen3-VL 32B Instruct33.36B20.9 GB1744.6
DeepSeek Coder 33B33B20.7 GB1726.0
Vicuna 33B33B20.7 GB1717.2
LLaMA 1 30B33B20.7 GB1717.8