▸ AMD· CDNA 1.0

AMD Radeon Instinct MI100

VRAM

32 GB

HIGH-END

BANDWIDTH

1230

GB/S

MODELS Q4

255/331

77%

7B Q4 SPEED

~156

BLAZING

▸ MODEL COVERAGE @ Q477% OF ALL

▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B

~364

TOK/S

7B

~156

TOK/S

14B

~78

TOK/S

32B

~34

TOK/S

70B

—

39.4GB NEEDED

▸ SPECIFICATIONS

VRAM

32 GB

BANDWIDTH

1230 GB/s

FP16 COMPUTE

184.6 TFLOPS

TDP

300W

MEMORY

HBM2

ARCHITECTURE

CDNA 1.0

STREAM PROCESSORS

7,680

COMPUTE UNITS

120

PCIE

Gen 4 x16

MSRP

$5,000

254

FAST MODELS · >30 TOK/S

Real-time chat speed

255

USABLE · >10 TOK/S

Comfortable for all tasks

255

TOTAL COMPATIBLE

Fit in VRAM at Q4

▸ RENT IT IN THE CLOUD

Buying Radeon Instinct MI100 costs $15–$40k and isn’t practical for most teams. Spin one up by the hour instead:

Rent on RunPod →Or Vast.ai →

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· 255

nomic-embed-text-v1.5 100M0.1B

EMBEDDING·8K CTX· CHAT

TOK/S · 2% VRAM

GPT-2 124M0.124B

GPT2·1K CTX· CHAT

TOK/S · 2% VRAM

SmolLM2 135M0.135B

SMOLLM·2K CTX· CHAT

TOK/S · 2% VRAM

bge-large-en-v1.5 335M0.335B

EMBEDDING·1K CTX· CHAT

TOK/S · 2% VRAM

mxbai-embed-large-v10.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 2% VRAM

Snowflake Arctic Embed L0.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 2% VRAM

GPT-2 Medium 345M0.345B

GPT2·1K CTX· CHAT

TOK/S · 2% VRAM

SmolLM2 360M0.36B

SMOLLM·8K CTX· CHAT

TOK/S · 2% VRAM

Falcon-H1 0.5B0.5B

FALCON·128K CTX· CHAT

TOK/S · 2% VRAM

Qwen 1.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 2% VRAM

Qwen 2.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 2% VRAM

EMBEDDING·8K CTX· EMBEDDING

TOK/S · 3% VRAM

QWEN·32K CTX· CHAT· REASONING

TOK/S · 3% VRAM

GPT-2 Large 774M0.774B

GPT2·1K CTX· CHAT

TOK/S · 3% VRAM

Qwen 3.5 0.8B0.8B

QWEN·256K CTX· CHAT· CODING· MULTILINGUAL

TOK/S · 3% VRAM

Qwen3.5-0.8B0.9B

QWEN·256K CTX· CHAT

TOK/S · 3% VRAM

FALCON·32K CTX· CHAT

TOK/S · 3% VRAM

INTERNLM·32K CTX· CHAT

TOK/S · 3% VRAM

TinyLlama 1.1B1.1B

LLAMA·2K CTX· CHAT

TOK/S · 4% VRAM

LFM2.5-1.2B-Thinking1.2B

LFM·122K CTX· CHAT· REASONING· TOOL_USE

TOK/S · 4% VRAM

Llama-3.2-1B1.2B

LLAMA·4K CTX· CHAT

TOK/S · 4% VRAM

DeepSeek Coder 1.3B1.3B

DEEPSEEK·16K CTX· CODING

TOK/S · 4% VRAM

EXAONE-4.0-1.2B1.3B

EXAONE·64K CTX· CHAT

TOK/S · 4% VRAM

OPT·2K CTX· CHAT

TOK/S · 4% VRAM

PHI·2K CTX· CODING

TOK/S · 4% VRAM

Phi-1.5 1.3B1.3B

PHI·2K CTX· CHAT· CODING

TOK/S · 4% VRAM

granite-4.0-h-tiny 6.9B6.9BMoE

GRANITE·128K CTX· CHAT

TOK/S · 15% VRAM

Falcon-H1 1.5B1.5B

FALCON·128K CTX· CHAT· CODING

TOK/S · 4% VRAM

GPT-2 XL 1.5B1.5B

GPT2·1K CTX· CHAT

TOK/S · 4% VRAM

Qwen2.5-Coder-1.5B1.5B

QWEN·32K CTX· CHAT· TOOL_USE· CODING

TOK/S · 4% VRAM

Qwen2 Math 1.5B1.5B

QWEN·4K CTX· REASONING

TOK/S · 4% VRAM

Qwen 2.5 1.5B1.5B

QWEN·32K CTX· CHAT· CODING

TOK/S · 4% VRAM

Yi Coder 1.5B1.5B

YI·125K CTX· CODING

TOK/S · 4% VRAM

stablelm-2-1_6b1.6B

STABLELM·4K CTX· CHAT

TOK/S · 5% VRAM

QWEN·32K CTX· CHAT· REASONING

TOK/S · 5% VRAM

SmolLM2 1.7B1.71B

SMOLLM·8K CTX· CHAT

TOK/S · 5% VRAM

Qwen 1.5 1.8B1.8B

QWEN·32K CTX· CHAT

TOK/S · 5% VRAM

Moondream2 1.9B1.9B

OTHER·2K CTX· VISION· CHAT

TOK/S · 5% VRAM

GEMMA·8K CTX· CHAT

TOK/S · 5% VRAM

Granite 3.0 2B2B

GRANITE·128K CTX· CHAT· CODING

TOK/S · 5% VRAM

▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon Instinct MI100.

▸Find models for Radeon Instinct MI100 Compare with other GPUs

▸ DEVICE UNDER TEST

AMD Radeon Instinct MI100 — 32 GB VRAM.

▸ RADEON INSTINCT MI100 SPEC

BRAND: AMD
VRAM: 32 GB HBM2
BANDWIDTH: 1230 GB/s
FP16 COMPUTE: 184.6 TFLOPS
FP32 COMPUTE: 23.1 TFLOPS
STREAM PROCESSORS: 7,680
TDP: 300 W
ARCHITECTURE: CDNA 1.0
MSRP: $5000

▸ AI CAPABILITY

255/ 331 models @ Q4

With 32 GB VRAM and 1230 GB/s bandwidth, this GPU handles models up to 41.9B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~141 tok/s.

§ 01TOP MODELS FOR RADEON INSTINCT MI100

255 FIT · SHOWING 20

MODEL	SIZE	VRAM Q4	TOK/S	AVG
Phi-3.5 MoE 42B	41.9B	26.1 GB	166	56.7
Falcon 40B	40B	24.9 GB	27	20.9
Qwen3.5-35B-A3B	36B	22.5 GB	30	48.5
c4ai-command-r-v01 35B	35B	21.9 GB	31	27.5
Qwen 3.5 35B A3B	35B	21.9 GB	364	53.3
Qwen 3.6 35B A3B	35B	21.9 GB	364	62.7
Nous Capybara 34B	34.4B	21.5 GB	32	42.0
Yi-1.5 34B	34.4B	21.5 GB	32	45.3
Falcon-H1 34B	34B	21.3 GB	32	66.1
CodeLlama 34B	34B	21.3 GB	32	25.4
Nous Hermes 2 34B	34B	21.3 GB	32	47.0
Phind CodeLlama 34B	34B	21.3 GB	32	68.1
LLaVA-1.6 Yi 34B	34B	21.3 GB	32	47.4
WizardCoder Python 34B	34B	21.3 GB	32	73.2
Yi 34B	34B	21.3 GB	32	33.4
DeepSeek Coder 33B	33B	20.7 GB	33	26.0
Vicuna 33B	33B	20.7 GB	33	17.2
LLaMA 1 30B	33B	20.7 GB	33	17.8
DeepSeek-R1-Distill-Qwen-32B	32.8B	20.5 GB	33	46.9
Qwen3 32B	32.8B	20.5 GB	33	54.9