NVIDIA · Ada Lovelace · 48 GB VRAM tier

Best AI Models for NVIDIA RTX 6000 Ada Generation (48 GB)

Runs 27–31B and 35B MoE models well; 70B only just fits.

48 GB GDDR6960 GB/s364 TFLOPS FP16300 WAda Lovelace 2022

What LLMs can the RTX 6000 Ada Generation run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 30.6 t/s	30.6 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 165 t/s	165 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 193 t/s	193 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 30.6 t/s	30.6 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 146 t/s	146 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 165 t/s	165 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 193 t/s	193 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 30.6 t/s	30.6 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 165 t/s	165 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 193 t/s	193 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 · 35.8 t/s	35.8 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 35.8 t/s	35.8 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 146 t/s	146 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 30.6 t/s	30.6 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 193 t/s	193 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 191 t/s	191 tok/s	Q4_K_M · 3.4 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 193 t/s	193 tok/s	Q4_K_M · 19.3 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 183 t/s	183 tok/s	Q4_K_M · 13.1 GB
4	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 169 t/s	169 tok/s	Q4_K_M · 19.4 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 165 t/s	165 tok/s	Q4_K_M · 16.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 35.8 t/s	35.8 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 30.6 t/s	30.6 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 165 t/s	165 tok/s	Q4_K_M · 16.5 GB
5	MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 163 t/s	163 tok/s	Q4_K_M · 22.1 GB

See all 368 models on the RTX 6000 Ada Generation →Best quant that fits · speeds estimated on this card

About the RTX 6000 Ada Generation

The RTX 6000 Ada Generation runs 27–31B and 35B MoE models well. Ada Lovelace generation, released 2022.

GenerationAda Lovelacereleased 2022

RTX 6000 Ada Generation strengths and weaknesses

Strengths

Runs 70B models: Llama 3.3 70B Instruct at 15.0 tok/s in 46.4 GB
Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 30.1 GB free
Reads long prompts fast: A 4K-token prompt on Qwen3.8 27B starts answering in 1.4 s

Weaknesses

120B MoE models don't fit: GPT OSS 120B needs 70.8 GB at Q4 vs 48 GB here

RTX 6000 Ada Generation tokens per second by model size

Output speed depends on memory bandwidth (960 GB/s). Grey rows need more than 48 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
98.1tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
65.7tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
35.8tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
146tok/s
70BLlama 3.3 70B Instruct · IQ4_XS · 46.4 GB tight · IQ4_XS
15.0tok/s
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 1216 models on the RTX 6000 Ada Generation

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 6000 Ada Generation — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
AI21 Jamba Reasoning 3B3.2BChatReasoningFunctions Q4_K_M·277.3 t/s	Q4_K_M	2.3 GB5%	277.3 t/s	262K	S100, Runs great
Tiny GptOssForCausalLM3MChatFunctions Q4_K_M·2080.0 t/s	Q4_K_M	0.6 GB1%	2080.0 t/s	131K	S100, Runs great
GPT OSS 20B Heretic Ara v321.5BChat Q4_K_M·165.0 t/s	Q4_K_M	13.5 GB28%	165.0 t/s	131K	S98, Runs great
Moondream21.9BVision Q4_K_M·491.3 t/s	Q4_K_M	3.0 GB6%	491.3 t/s	—	S100, Runs great
UI TARS 1.5 7B8.3BVisionFunctions Q4_K_M·115.8 t/s	Q4_K_M	6.2 GB13%	115.8 t/s	128K	S94, Runs great
Gemma 3 12B IT Heretic v212.2BChat Q4_K_M·74.6 t/s	Q4_K_M	9.2 GB19%	74.6 t/s	131K	S86, Runs great
LocoTrainer 4B4.0BChatCodeFunctions Q4_K_M·215.2 t/s	Q4_K_M	4.2 GB9%	215.2 t/s	262K	S100, Runs great
Nandi Mini V1.1 600M Intermediate Checkpoint 400GT649MChat BF16·350.6 t/s	BF16	1.8 GB4%	350.6 t/s	2K	S100, Runs great
Sarvam 30B Uncensored32.2BChat Q4_K_M·182.9 t/s	Q4_K_M	19.9 GB41%	182.9 t/s	131K	S99, Runs great
Supra Mini V5 8M8MChat Q4_K_M·1950.0 t/s	Q4_K_M	0.3 GB1%	1950.0 t/s	1K	S100, Runs great
Domyn Small v1.09.8BChatReasoning Q4_K_M·97.3 t/s	Q4_K_M	8.0 GB17%	97.3 t/s	33K	S91, Runs great
Kimi K2.6 Eagle31.8BChat Q4_K_M·427.4 t/s	Q4_K_M	1.9 GB4%	427.4 t/s	262K	S100, Runs great
Bella Bartender 8B Llama3.18.0BChat Q4_K_M·115.8 t/s	Q4_K_M	7.3 GB15%	115.8 t/s	131K	S94, Runs great
Tongyi DeepResearch 30B A3B30.5BChat Q4_K_M·168.5 t/s	Q4_K_M	19.4 GB40%	168.5 t/s	131K	S98, Runs great
SmolVLM2 256M Video Instruct256MVision Q4_K_M·1248.0 t/s	Q4_K_M	0.6 GB1%	1248.0 t/s	8K	S100, Runs great

Rent NVIDIA RTX 6000 Ada Generation in the cloud

Hourly rate on demand for one RTX 6000 Ada Generation.

Vast.aiMarketplaceLowest price
from$0.68/hr
Deploy
RunPod$5+ bonus credit
from$0.74/hr
Deploy

Buying one ($6,799) costs as much as ~10,000 hours of rental, about 42 months at 8 hours a day.

Cost per million tokens

Output-token cost on an RTX 6000 Ada Generation rented at $0.68/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	193 tok/s	$0.98$0.0054 input
Gemma 4 26B A4B IT	Q4_K_M	165 tok/s	$1.14$0.010 input
Qwen3.6 35B A3B	Q4_K_M	146 tok/s	$1.29$0.011 input
Qwen3.8 27B	Q4_K_M	36 tok/s	$5.27$0.064 input
Muse Glimmer 30B	Q4_K_M	34 tok/s	$5.55$0.069 input

RTX 6000 Ada Generation specs, power and PSU

Specs

Architecture: Ada Lovelace
VRAM: 48 GB GDDR6
Memory bandwidth: 960.0 GB/s
FP16 (dense): 364.30 TFLOPS
CUDA cores: 18,176
Tensor cores: 568
Compute capability: 8.9
TDP: 300 W
Released: 2022-12-03
MSRP: $6,799

RTX 6000 Ada Generation FAQ

What is the largest model the RTX 6000 Ada Generation 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 14.9 tok/s.

Can the RTX 6000 Ada Generation 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 6000 Ada Generation 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 6000 Ada Generation give?

About 35.8 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 1.4 s on a 4K-token prompt.

What power supply does the RTX 6000 Ada Generation 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 36 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

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