FitMyLLM
▸ NVIDIA· ADA LOVELACE

NVIDIA RTX 4000 Ada 20GB

VRAM
20 GB
MID-RANGE
BANDWIDTH
432
GB/S
MODELS Q4
285/449
63%
7B Q4 SPEED
~49
FAST
▸ MODEL COVERAGE @ Q463% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~115
TOK/S
7B
~49
TOK/S
14B
~25
TOK/S
32B
~11
TOK/S
70B
—
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
20 GB
BANDWIDTH
432 GB/s
FP16 COMPUTE
212 TFLOPS
TDP
130W
MEMORY
GDDR6
ARCHITECTURE
Ada Lovelace
CUDA CORES
6,144
TENSOR CORES
192
PCIE
Gen 4 x16
MSRP
$1,250
232
FAST MODELS · >30 TOK/S
Real-time chat speed
285
USABLE · >10 TOK/S
Comfortable for all tasks
285
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test RTX 4000 Ada 20GB (or anything bigger) without committing. Pay by the second, cancel anytime.

Rent on Vast.ai →Or RunPod →

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· 285
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
3840
TOK/S · 3% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
2560
TOK/S · 3% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
2469
TOK/S · 3% VRAM
›
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
2469
TOK/S · 3% VRAM
›
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
1350
TOK/S · 3% VRAM
›
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
1280
TOK/S · 3% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
1133
TOK/S · 3% VRAM
›
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
1032
TOK/S · 3% VRAM
›
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
1032
TOK/S · 3% VRAM
›
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
1032
TOK/S · 3% VRAM
›
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
987
TOK/S · 4% VRAM
›
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
960
TOK/S · 4% VRAM
›
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
909
TOK/S · 4% VRAM
›
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
691
TOK/S · 4% VRAM
›
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
691
TOK/S · 4% VRAM
›
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
665
TOK/S · 4% VRAM
›
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
608
TOK/S · 4% VRAM
›
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
608
TOK/S · 4% VRAM
›
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
576
TOK/S · 4% VRAM
›
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
576
TOK/S · 4% VRAM
›
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
576
TOK/S · 4% VRAM
›
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
557
TOK/S · 4% VRAM
›
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
467
TOK/S · 5% VRAM
›
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
461
TOK/S · 5% VRAM
›
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
427
TOK/S · 5% VRAM
›
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
397
TOK/S · 5% VRAM
›
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
368
TOK/S · 5% VRAM
›
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
320
TOK/S · 6% VRAM
›
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
314
TOK/S · 6% VRAM
›
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
288
TOK/S · 6% VRAM
›
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
288
TOK/S · 6% VRAM
›
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
288
TOK/S · 6% VRAM
›
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
288
TOK/S · 6% VRAM
›
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
266
TOK/S · 6% VRAM
›
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
266
TOK/S · 6% VRAM
›
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
266
TOK/S · 6% VRAM
›
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
256
TOK/S · 7% VRAM
›
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
243
TOK/S · 7% VRAM
›
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
243
TOK/S · 7% VRAM
›
S
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
230
TOK/S · 28% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your RTX 4000 Ada 20GB.

▸Find models for RTX 4000 Ada 20GBCompare with other GPUs
▸ DEVICE UNDER TEST

NVIDIA RTX 4000 Ada 20GB — 20 GB VRAM.

▸ RTX 4000 ADA 20GB SPEC
BRAND
NVIDIA
VRAM
20 GB GDDR6
BANDWIDTH
432 GB/s
FP16 COMPUTE
212 TFLOPS
FP32 COMPUTE
26.7 TFLOPS
CUDA CORES
6,144
TENSOR CORES
192
TDP
130 W
ARCHITECTURE
Ada Lovelace
MSRP
$1250
▸ AI CAPABILITY
285/ 449 models @ Q4

With 20 GB VRAM and 432 GB/s bandwidth, this GPU handles models up to 28B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~49 tok/s.

§ 01TOP MODELS FOR RTX 4000 ADA 20GB
285 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
PaliGemma 2 28B28B17.6 GB1238.6
ERNIE 4.5 VL 28B A3B Thinking28B17.6 GB115—
Qwen3.5-27B27.8B17.5 GB1259.4
Qwen 3.8 27B27.78B17.5 GB1270.1
gemma-3-27b27.4B17.2 GB1327.2
gemma-2-27b27.2B17.1 GB1334.6
Qwen 3.6 27B27B17.0 GB1341.1
Gemma 4 26B A4B26B16.4 GB8647.9
Aria 25B A3.9B25.3B16.0 GB8964.8
Mistral-Small-24B24B15.2 GB1425.0
Mistral-Small-3.1-24B24B15.2 GB1428.8
Magistral Small 24B24B15.2 GB1447.0
Devstral Small 2 24B24B15.2 GB1433.4
Mistral-Small-3.2-24B24B15.2 GB1444.4
LFM2 24B A2B24B15.2 GB17319.1
Devstral Small 22B23.57B14.9 GB1535.5
Codestral 22B22.2B14.1 GB1650.1
Mistral Small 22B22.2B14.1 GB1635.2
SOLAR-Pro 22B22.1B14.0 GB1644.2
ERNIE 4.5 21B A3B21.95B13.9 GB115—