llmrun

NVIDIA · Ampere · 48 GB VRAM tier

Best AI Models for NVIDIA RTX A6000 (48 GB)

Runs 27–31B and 35B MoE models well; 70B barely fits and is slow (12 tok/s).

48 GB GDDR6768 GB/s155 TFLOPS FP16300 WAmpere 2020

What LLMs can the RTX A6000 run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.8 27BAlibabaHow to run →
Q4_K_M · 17.9 GB · 28.7 t/s
28.7 tok/sQ4_K_M · 17.9 GB
2
Qwen3.6 27BAlibaba
Q4_K_M · 17.9 GB · 28.7 t/s
28.7 tok/sQ4_K_M · 17.9 GB
3
Gemma 4 31B ITGoogle
Q4_K_M · 21.7 GB · 24.5 t/s
24.5 tok/sQ4_K_M · 21.7 GB
4
Gemma 4 26B A4B ITGoogle
Q4_K_M · 16.5 GB · 140 t/s
140 tok/sQ4_K_M · 16.5 GB
5
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA
Q4_K_M · 19.3 GB · 174 t/s
174 tok/sQ4_K_M · 19.3 GB
See all 368 models on the RTX A6000 →Best quant that fits · speeds estimated on this card

About the RTX A6000

The RTX A6000 runs 27–31B and 35B MoE models well. Ampere generation, released 2020.

GenerationAmperereleased 2020

RTX A6000 strengths and weaknesses

Strengths

  • Runs 35B MoE models: Qwen3.6 35B A3B at 125 tok/s in 22 GB
  • Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 30.1 GB free

Weaknesses

  • 120B MoE models don't fit: GPT OSS 120B needs 70.8 GB at Q4 vs 48 GB here
  • No FP8 or NVFP4: Ampere predates both; use GGUF, AWQ or GPTQ builds

RTX A6000 tokens per second by model size

Output speed depends on memory bandwidth (768 GB/s). Grey rows need more than 48 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    78.5tok/s
  2. 14BQwen3 14B · Q4_K_M · 11.9 GB
    52.5tok/s
  3. 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
    28.7tok/s
  4. 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
    125tok/s
  5. 70BLlama 3.3 70B Instruct · IQ4_XS · 46.4 GB tight · IQ4_XS
    12.0tok/s
  6. 120B MoEGPT OSS 120B · not at 4-bit
    needs 70.8 GB

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

All 368 models on the RTX A6000

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 RTX A6000 — ranked by Score, recency and Fit
ModelVRAMScoreFit
Gemma 4 E2B
Q4_K_M·145.5 t/s
3.5 GBS97, Runs great
Ministral 8B Instruct 2410
Q4_K_M·92.3 t/s
7.5 GBS90, Runs great
Yi Coder 9B Chat
Q4_K_M·86.1 t/s
7.2 GBS88, Runs great
Gemma 3 1B IT
Q4_K_M·756.4 t/s
2.1 GBS100, Runs great
Yi 1.5 34B Chat
Q4_K_M·23.3 t/s
21.9 GBB64, Decent
Qwen2 VL 7B Instruct
Q4_K_M·92.6 t/s
6.2 GBS90, Runs great
Ling 3.0 Flash VL
IQ2_M·155.3 t/s
43.2 GBA83, Runs well
MiniCPM V 4 5
Q4_K_M·85.8 t/s
7.9 GBS88, Runs great
Mellum2 12B A2.5B Thinking
Q4_K_M·216.4 t/s
7.8 GBS100, Runs great
Mistral Small 24B Instruct 2501
Q4_K_M·33.6 t/s
17.8 GBA72, Runs well
Gemma 3n E2B IT
Q4_K_M·139.1 t/s
5.9 GBS96, Runs great
DeepSeek R1 Distill Qwen 7B
Q4_K_M·100.0 t/s
5.8 GBS91, Runs great
Gemma 4 12B
Q4_K_M·60.7 t/s
9.0 GBA84, Runs well
Gemma 3 4B Pt
Q4_K_M·175.8 t/s
5 GBS99, Runs great
Phi 4 Mini Instruct
Q4_K_M·173.9 t/s
4.8 GBS98, Runs great

Rent NVIDIA RTX A6000 in the cloud

Hourly rate on demand for one RTX A6000.

  • Vast.aiMarketplace

    from$0.47/hr

    Deploy

Buying one ($4,649) costs as much as ~9,800 hours of rental, about 41 months at 8 hours a day.

Cost per million tokens

Output-token cost on an RTX A6000 rented at $0.47/hr, one request at a time. Batch several users on the same card and the cost per token drops several-fold.

ModelSpeedPer 1M output
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16174 tok/s$0.76$0.0089 input
Gemma 4 26B A4B IT140 tok/s$0.94$0.017 input
Qwen3.6 35B A3B125 tok/s$1.05$0.018 input
Qwen3.8 27B29 tok/s$4.58$0.10 input
Muse Glimmer 30B27 tok/s$4.83$0.11 input

RTX A6000 specs, power and PSU

Specs

Architecture
Ampere
VRAM
48 GB GDDR6
Memory bandwidth
768.0 GB/s
FP16 (dense)
154.80 TFLOPS
CUDA cores
10,752
Tensor cores
336
Compute capability
8.6
TDP
300 W
Released
2020-10-05
MSRP
$4,649

RTX A6000 FAQ

What is the largest model the RTX A6000 can run?

Qwen2.5 72B Instruct (72.7B) is the largest at 4-bit or better: at Q4_K_S it uses 46.6 GB of 48 GB, and runs at about 11.9 tok/s.

Can the RTX A6000 run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 48 GB, and it is the best model that runs well on this card.

Can the RTX A6000 run 120B MoE models?

No. GPT OSS 120B needs 70.8 GB at Q4, more than the 48 GB on this card.

How many tokens per second does the RTX A6000 give?

About 28.7 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 3.3 s on a 4K-token prompt.

What power supply does the RTX A6000 need?

Plan a 600 W PSU (2× the 300 W TDP).

Is 48 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 10 coding models that fit, runs at about 29 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Related

Best coding LLMs48 GB VRAMGPUs with 48 GB or more