▸ NVIDIA· AMPERE

NVIDIA RTX A5500 Mobile

VRAM

16 GB

MID-RANGE

BANDWIDTH

512

GB/S

MODELS Q4

260/428

61%

7B Q4 SPEED

~59

BLAZING

▸ MODEL COVERAGE @ Q461% OF ALL

▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B

~137

TOK/S

7B

~59

TOK/S

14B

~29

TOK/S

32B

—

18.0GB NEEDED

70B

—

39.4GB NEEDED

▸ SPECIFICATIONS

VRAM

16 GB

BANDWIDTH

512 GB/s

FP16 COMPUTE

22.3 TFLOPS

TDP

165W

MEMORY

GDDR6

ARCHITECTURE

Ampere

CUDA CORES

7,424

TENSOR CORES

232

PCIE

Gen 4 x16

237

FAST MODELS · >30 TOK/S

Real-time chat speed

260

USABLE · >10 TOK/S

Comfortable for all tasks

260

TOTAL COMPATIBLE

Fit in VRAM at Q4

▸ RENT IT IN THE CLOUD

Buying RTX A5500 Mobile 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· 260

Falcon-H1R Tiny 90M0.09B

FALCON·256K CTX· CHAT· REASONING

TOK/S · 3% VRAM

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

EMBEDDING·8K CTX· CHAT

TOK/S · 3% VRAM

GPT-2 124M0.124B

GPT2·1K CTX· CHAT

TOK/S · 4% VRAM

SmolLM2 135M0.135B

SMOLLM·2K CTX· CHAT

TOK/S · 4% VRAM

SmolVLM 256M0.256B

SMOLLM·8K CTX· CHAT· VISION

TOK/S · 4% VRAM

Gemma 3 270M0.27B

GEMMA·32K CTX· CHAT

TOK/S · 4% VRAM

Snowflake Arctic Embed M v2.00.305B

EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL

TOK/S · 4% VRAM

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

EMBEDDING·1K CTX· CHAT

TOK/S · 4% VRAM

mxbai-embed-large-v10.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 4% VRAM

Snowflake Arctic Embed L0.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 4% VRAM

GPT-2 Medium 345M0.345B

GPT2·1K CTX· CHAT

TOK/S · 4% VRAM

LFM·125K CTX· CHAT· TOOL_USE

TOK/S · 4% VRAM

SmolLM2 360M0.36B

SMOLLM·8K CTX· CHAT

TOK/S · 4% VRAM

Falcon-H1 0.5B0.5B

FALCON·128K CTX· CHAT

TOK/S · 5% VRAM

Qwen 1.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 5% VRAM

Qwen 2.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 5% VRAM

SmolVLM 500M0.5B

SMOLLM·8K CTX· CHAT· VISION

TOK/S · 5% VRAM

EMBEDDING·8K CTX· EMBEDDING

TOK/S · 5% VRAM

Snowflake Arctic Embed L v2.00.568B

EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL

TOK/S · 5% VRAM

QWEN·32K CTX· CHAT· REASONING

TOK/S · 5% VRAM

Qwen3-Embedding 0.6B0.6B

EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL

TOK/S · 5% VRAM

Falcon-H1R Tiny 0.6B0.6B

FALCON·32K CTX· CHAT· REASONING

TOK/S · 5% VRAM

Falcon Perception 0.6B0.6B

FALCON·4K CTX· VISION

TOK/S · 5% VRAM

LFM·125K CTX· CHAT· TOOL_USE

TOK/S · 6% VRAM

GPT-2 Large 774M0.774B

GPT2·1K CTX· CHAT

TOK/S · 6% VRAM

Qwen 3.5 0.8B0.8B

QWEN·256K CTX· CHAT· CODING· MULTILINGUAL

TOK/S · 6% VRAM

Qwen3.5-0.8B0.9B

QWEN·256K CTX· CHAT

TOK/S · 6% VRAM

FALCON·32K CTX· CHAT

TOK/S · 7% VRAM

INTERNLM·32K CTX· CHAT

TOK/S · 7% VRAM

OTHER·32K CTX· CHAT· VISION

TOK/S · 7% VRAM

TinyLlama 1.1B1.1B

LLAMA·2K CTX· CHAT

TOK/S · 7% VRAM

LFM2.5-1.2B-Thinking1.2B

LFM·122K CTX· CHAT· REASONING· TOOL_USE

TOK/S · 8% VRAM

Llama-3.2-1B1.2B

LLAMA·4K CTX· CHAT

TOK/S · 8% VRAM

LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL

TOK/S · 8% VRAM

Zamba2 1.2B1.2B

OTHER·4K CTX· CHAT

TOK/S · 8% VRAM

DeepSeek Coder 1.3B1.3B

DEEPSEEK·16K CTX· CODING

TOK/S · 8% VRAM

EXAONE-4.0-1.2B1.3B

EXAONE·64K CTX· CHAT

TOK/S · 8% VRAM

OPT·2K CTX· CHAT

TOK/S · 8% VRAM

PHI·2K CTX· CODING

TOK/S · 8% VRAM

Phi-1.5 1.3B1.3B

PHI·2K CTX· CHAT· CODING

TOK/S · 8% VRAM

▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your RTX A5500 Mobile.

▸Find models for RTX A5500 Mobile Compare with other GPUs

▸ DEVICE UNDER TEST

NVIDIA RTX A5500 Mobile — 16 GB VRAM.

▸ RTX A5500 MOBILE SPEC

BRAND: NVIDIA
VRAM: 16 GB GDDR6
BANDWIDTH: 512 GB/s
FP16 COMPUTE: 22.3 TFLOPS
FP32 COMPUTE: 22.3 TFLOPS
CUDA CORES: 7,424
TENSOR CORES: 232
TDP: 165 W
ARCHITECTURE: Ampere

▸ AI CAPABILITY

260/ 428 models @ Q4

With 16 GB VRAM and 512 GB/s bandwidth, this GPU handles models up to 22.2B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~59 tok/s.

§ 01TOP MODELS FOR RTX A5500 MOBILE

260 FIT · SHOWING 20

MODEL	SIZE	VRAM Q4	TOK/S	AVG
Codestral 22B	22.2B	14.1 GB	18	50.1
Devstral Small 22B	22.2B	14.1 GB	18	35.5
Mistral Small 22B	22.2B	14.1 GB	18	35.2
SOLAR-Pro 22B	22.1B	14.0 GB	19	44.2
ERNIE 4.5 21B A3B	21B	13.3 GB	137	—
GPT-OSS 20B	21B	13.3 GB	114	52.9
Reka Flash 3	21B	13.3 GB	20	36.2
Reka Flash 3.1	21B	13.3 GB	20	33.4
InternLM2 20B	19.8B	12.6 GB	21	45.1
InternLM2.5 20B	19.8B	12.6 GB	21	50.9
Ling-lite 16.8B	16.8B	10.8 GB	171	—
DeepSeek V2 Lite 16B	16B	10.3 GB	171	38.0
DeepSeek-Coder-V2-Lite 15.7B	15.7B	10.1 GB	171	43.0
DeepSeek-VL2 Small 16B	15.7B	10.1 GB	171	43.1
StarCoder 15B	15.5B	10.0 GB	26	21.0
StarCoder2 15B	15B	9.7 GB	27	26.5
Phi-4-reasoning-vision 15B	15B	9.7 GB	27	42.8
DeepSeek R1 Distill Qwen 14B	14.8B	9.5 GB	28	43.9
DeepCoder 14B	14.8B	9.5 GB	28	38.7
Qwen2.5-Coder-14B	14.8B	9.5 GB	28	41.3