NVIDIA · Ampere

Best AI Models for NVIDIA A100 80GB SXM

Runs everything up to 120B MoE well.

80 GB HBM2e2039 GB/s312 TFLOPS FP16400 WAmpere 2020

What LLMs can the A100 80GB SXM run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 228 t/s	228 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Math Score	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 228 t/s	228 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 407 t/s	407 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 305 t/s	305 tok/s	Q4_K_M · 13.1 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
4	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 253 t/s	253 tok/s	Q4_K_M · 19.3 GB
5	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 239 t/s	239 tok/s	Q4_K_M · 19.4 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 65.0 t/s	65.0 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 269 t/s	269 tok/s	Q4_K_M · 16.5 GB
5	JEV 27B VLautotrust Q4_K_M · 17.9 GB · 76.1 t/s	76.1 tok/s	Q4_K_M · 17.9 GB

See all 383 models on the A100 80GB SXM →Best quant that fits · speeds estimated on this card

About the A100 80GB SXM

The A100 80GB SXM runs everything up to 120B MoE well. Ampere generation, released 2020.

GenerationAmperereleased 2020

A100 80GB SXM strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 218 tok/s in 70.8 GB
Room for long context: Llama 3.3 70B Instruct at Q4 uses 51.3 GB, leaving 28.7 GB free
Reads long prompts fast: A 4K-token prompt on Qwen3.8 27B starts answering in 1.6 s

Weaknesses

No FP8 or NVFP4: Ampere predates both; use GGUF, AWQ or GPTQ builds

A100 80GB SXM tokens per second by model size

Output speed depends on memory bandwidth (2039 GB/s).

9BQwen3.5 9B · Q4_K_M · 6.6 GB
208tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
140tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
76.1tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
228tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
28.5tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
218tok/s

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 1258 models on the A100 80GB SXM

Featured only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with NVIDIA A100 80GB SXM — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
MiniMax M2.5228.7BChatFunctions IQ2_M·160.3 t/s	IQ2_M	79.6 GB99%	160.3 t/s	197K	C44, Usable
Llama Guard 3 1B1.5BChat Q4_K_M·1338.7 t/s	Q4_K_M	2.6 GB3%	1338.7 t/s	—	S100, Runs great
Mellum2 12B A2.5B Thinking SFT12.1BChat Q4_K_M·370.3 t/s	Q4_K_M	7.8 GB10%	370.3 t/s	131K	S100, Runs great
Glm 4 9B Chat9.4BChatFunctions Q4_K_M·213.8 t/s	Q4_K_M	8.9 GB11%	213.8 t/s	131K	S100, Runs great
Mixtral 8x7B v0.146.7BChat Q4_K_M·129.7 t/s	Q4_K_M	30.5 GB38%	129.7 t/s	33K	S95, Runs great
Covenant 72B72.7BChat Q4_K_M·29.7 t/s	Q4_K_M	44.6 GB56%	29.7 t/s	2K	A71, Runs well
Qwen1.5 0.5B Chat620MChat Q4_K_M·1523.4 t/s	Q4_K_M	2.3 GB3%	1523.4 t/s	33K	S100, Runs great
Qwen2.5 Coder 0.5B Instruct494MChatCodeFunctions Q4_K_M·2137.7 t/s	Q4_K_M	0.8 GB1%	2137.7 t/s	33K	S100, Runs great
Kumru 2B Base2.4BChat Q4_K_M·720.3 t/s	Q4_K_M	2.2 GB3%	720.3 t/s	8K	S100, Runs great
Tiny Starcoder Py164MChatCode Q4_K_M·12048.6 t/s	Q4_K_M	0.5 GB1%	12048.6 t/s	8K	S100, Runs great
C4ai Command R V0135.0BChatFunctions Q4_K_M·57.4 t/s	Q4_K_M	27.0 GB34%	57.4 t/s	—	A82, Runs well
Gemma 3 270M268MChat Q4_K_M·7363.1 t/s	Q4_K_M	1.2 GB1%	7363.1 t/s	—	S100, Runs great
Phi 3.5 Mini Instruct3.8BChatCode Q4_K_M·389.8 t/s	Q4_K_M	9.0 GB11%	389.8 t/s	131K	S100, Runs great
Tiny BloomForCausalLM2MChat Q4_K_M·132535.0 t/s	Q4_K_M	0.3 GB0%	132535.0 t/s	—	S100, Runs great
Wildguard7.2BChat Q4_K_M·277.3 t/s	Q4_K_M	7.3 GB9%	277.3 t/s	—	S100, Runs great

Rent NVIDIA A100 80GB SXM in the cloud

Hourly rate on demand for one A100 80GB SXM.

Vast.aiMarketplaceLowest price
from$1.26/hr
Deploy
RunPod$5+ bonus credit
from$1.39/hr
Deploy

Cost per million tokens

Output-token cost on an A100 80GB SXM rented at $1.26/hr, one request at a time. Batch several users on the same card and the cost per token drops several-fold.

Model	Quant	Speed	Per 1M output
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16	Q4_K_M	253 tok/s	$1.38$0.012 input
GLM 4.7 Flash	Q4_K_M	209 tok/s	$1.67$0.023 input
Qwen3.8 27B	Q4_K_M	76 tok/s	$4.58$0.14 input
Muse Glimmer 30B	Q4_K_M	72 tok/s	$4.82$0.15 input
Gemma 4 31B IT	Q4_K_M	65 tok/s	$5.37$0.16 input

A100 80GB SXM specs, power and PSU

Specs

Architecture: Ampere
VRAM: 80 GB HBM2e
Memory bandwidth: 2039.0 GB/s
FP16 (dense): 312.00 TFLOPS
CUDA cores: 6,912
Tensor cores: 432
Compute capability: 8.0
TDP: 400 W
Released: 2020-11-16

A100 80GB SXM FAQ

What is the largest model the A100 80GB SXM can run?

Mistral Medium 3.5 128B (127.7B) is the largest at 4-bit or better: at Q4_K_S it uses 78.0 GB of 80 GB, and runs at about 18.2 tok/s.

Can the A100 80GB SXM run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 80 GB, and it is the best model that runs well on this card.

How many tokens per second does the A100 80GB SXM give?

About 76.1 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 1.6 s on a 4K-token prompt.

What power supply does the A100 80GB SXM need?

Plan a 800 W PSU (2× the 400 W TDP).

Is 80 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 12 coding models that fit, runs at about 76 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Best coding LLMs 48 GB VRAM GPUs with 80 GB or more