AMD· CDNA 4.0

AMD Radeon Instinct MI355X

VRAM
288 GB
FLAGSHIP
BANDWIDTH
8190
GB/S
MODELS Q4
318/331
96%
7B Q4 SPEED
~1040
BLAZING
▸ MODEL COVERAGE @ Q496% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~2427
TOK/S
7B
~1040
TOK/S
14B
~520
TOK/S
32B
~228
TOK/S
70B
~104
TOK/S
▸ SPECIFICATIONS
VRAM
288 GB
BANDWIDTH
8190 GB/s
FP16 COMPUTE
629.1 TFLOPS
TDP
1400W
MEMORY
HBM3e
ARCHITECTURE
CDNA 4.0
STREAM PROCESSORS
16,384
COMPUTE UNITS
128
PCIE
Gen 5 x16
MSRP
$30,000
315
FAST MODELS · >30 TOK/S
Real-time chat speed
318
USABLE · >10 TOK/S
Comfortable for all tasks
318
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ RENT IT IN THE CLOUD

Buying Radeon Instinct MI355X costs $15–$40k and isn’t practical for most teams. Spin one up by the hour instead:

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· 318
S
nomic-embed-text-v1.5 100M0.1B
EMBEDDING·8K CTX· CHAT
72800
TOK/S · 0% VRAM
S
GPT-2 124M0.124B
GPT2·1K CTX· CHAT
58710
TOK/S · 0% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
53926
TOK/S · 0% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
21731
TOK/S · 0% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
21731
TOK/S · 0% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
21731
TOK/S · 0% VRAM
S
GPT-2 Medium 345M0.345B
GPT2·1K CTX· CHAT
21101
TOK/S · 0% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
20222
TOK/S · 0% VRAM
S
Falcon-H1 0.5B0.5B
FALCON·128K CTX· CHAT
14560
TOK/S · 0% VRAM
S
Qwen 1.5 0.5B0.5B
QWEN·32K CTX· CHAT
14560
TOK/S · 0% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
14560
TOK/S · 0% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
12817
TOK/S · 0% VRAM
S
Qwen3 0.6B0.6B
QWEN·32K CTX· CHAT· REASONING
12133
TOK/S · 0% VRAM
S
GPT-2 Large 774M0.774B
GPT2·1K CTX· CHAT
9406
TOK/S · 0% VRAM
S
Qwen 3.5 0.8B0.8B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
9100
TOK/S · 0% VRAM
S
Qwen3.5-0.8B0.9B
QWEN·256K CTX· CHAT
8089
TOK/S · 0% VRAM
S
Falcon3-1B1B
FALCON·32K CTX· CHAT
7280
TOK/S · 0% VRAM
S
InternLM2 1B1B
INTERNLM·32K CTX· CHAT
7280
TOK/S · 0% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
6618
TOK/S · 0% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
6067
TOK/S · 0% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
6067
TOK/S · 0% VRAM
S
DeepSeek Coder 1.3B1.3B
DEEPSEEK·16K CTX· CODING
5600
TOK/S · 0% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
5600
TOK/S · 0% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
5600
TOK/S · 0% VRAM
S
Phi-1 1.3B1.3B
PHI·2K CTX· CODING
5600
TOK/S · 0% VRAM
S
Phi-1.5 1.3B1.3B
PHI·2K CTX· CHAT· CODING
5600
TOK/S · 0% VRAM
S
granite-4.0-h-tiny 6.9B6.9BMoE
GRANITE·128K CTX· CHAT
4853
TOK/S · 2% VRAM
S
Falcon-H1 1.5B1.5B
FALCON·128K CTX· CHAT· CODING
4853
TOK/S · 0% VRAM
S
GPT-2 XL 1.5B1.5B
GPT2·1K CTX· CHAT
4853
TOK/S · 0% VRAM
S
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
4853
TOK/S · 0% VRAM
S
Qwen2 Math 1.5B1.5B
QWEN·4K CTX· REASONING
4853
TOK/S · 0% VRAM
S
Qwen 2.5 1.5B1.5B
QWEN·32K CTX· CHAT· CODING
4853
TOK/S · 0% VRAM
S
Yi Coder 1.5B1.5B
YI·125K CTX· CODING
4853
TOK/S · 0% VRAM
S
stablelm-2-1_6b1.6B
STABLELM·4K CTX· CHAT
4550
TOK/S · 1% VRAM
S
Qwen3 1.7B1.7B
QWEN·32K CTX· CHAT· REASONING
4282
TOK/S · 1% VRAM
S
SmolLM2 1.7B1.71B
SMOLLM·8K CTX· CHAT
4257
TOK/S · 1% VRAM
S
Qwen 1.5 1.8B1.8B
QWEN·32K CTX· CHAT
4044
TOK/S · 1% VRAM
S
Moondream2 1.9B1.9B
OTHER·2K CTX· VISION· CHAT
3832
TOK/S · 1% VRAM
S
Gemma 1 2B2B
GEMMA·8K CTX· CHAT
3640
TOK/S · 1% VRAM
S
Granite 3.0 2B2B
GRANITE·128K CTX· CHAT· CODING
3640
TOK/S · 1% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon Instinct MI355X.

▸ DEVICE UNDER TEST

AMD Radeon Instinct MI355X288 GB VRAM.

RADEON INSTINCT MI355X SPEC
BRAND
AMD
VRAM
288 GB HBM3e
BANDWIDTH
8190 GB/s
FP16 COMPUTE
629.1 TFLOPS
FP32 COMPUTE
78.6 TFLOPS
STREAM PROCESSORS
16,384
TDP
1400 W
ARCHITECTURE
CDNA 4.0
MSRP
$30000
▸ AI CAPABILITY
318/ 331 models @ Q4

With 288 GB VRAM and 8190 GB/s bandwidth, this GPU handles models up to 405B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~936 tok/s.

§ 01TOP MODELS FOR RADEON INSTINCT MI355X
318 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Llama 3.1 405B405B248.0 GB1848.4
Llama-4-Maverick-17B-128E400B245.0 GB42846.1
Qwen3.5-397B-A17B397B243.2 GB42868.4
GLM 4.7358B219.3 GB22864.4
GLM 4.6357B218.7 GB60741.4
GLM 4.5355B217.5 GB60747.8
Nemotron-4 340B340B208.3 GB2165.4
MiMo V2 Flash 309B309B189.4 GB48572.4
ERNIE-4.5-300B-A47B-Paddle300.5B184.2 GB2437.4
ERNIE 4.5 300B-A47B300B183.9 GB15549.8
DeepSeek V4 Flash284B174.1 GB56072.3
DeepSeek V2 236B236B144.7 GB34740.4
DeepSeek-V2.5 236B236B144.7 GB34764.0
DeepSeek-Coder-V2 236B236B144.7 GB34761.8
Qwen3-235B-A22B235.1B144.2 GB33155.9
MiniMax-M2.5 228.7B228.7B140.3 GB34762.6
Falcon 180B180B110.5 GB4051.3
bloom 176.2B176.2B108.2 GB4115.0
dots.llm1.inst 142.8B142.8B87.8 GB51
WizardLM 2 8x22B141B86.7 GB18742.4