▸ NVIDIA· AMPERE

NVIDIA GRID A100B

VRAM

48 GB

FLAGSHIP

BANDWIDTH

1870

GB/S

MODELS Q4

345/449

77%

7B Q4 SPEED

~214

BLAZING

▸ MODEL COVERAGE @ Q477% OF ALL

▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

~499

TOK/S

~214

TOK/S

14B

~107

TOK/S

32B

~47

TOK/S

70B

~21

TOK/S

▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS →

▸ SPECIFICATIONS

VRAM

48 GB

BANDWIDTH

1870 GB/s

FP16 COMPUTE

55.6 TFLOPS

TDP

400W

MEMORY

HBM2e

ARCHITECTURE

Ampere

CUDA CORES

6,912

TENSOR CORES

432

PCIE

Gen 4 x16

344

FAST MODELS · >30 TOK/S

Real-time chat speed

345

USABLE · >10 TOK/S

Comfortable for all tasks

345

TOTAL COMPATIBLE

Fit in VRAM at Q4

▸ RENT IT IN THE CLOUD

Buying GRID A100B costs $15–$40k and isn’t practical for most teams. Spin one up by the hour instead:

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· 345

Falcon-H1R Tiny 90M0.09B

FALCON·256K CTX· CHAT· REASONING

nomic-embed-text-v1.5 100M0.14B

EMBEDDING·8K CTX· CHAT

SMOLLM·8K CTX· CHAT· VISION

Snowflake Arctic Embed M v2.00.305B

EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL

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

EMBEDDING·1K CTX· CHAT

mxbai-embed-large-v10.335B

EMBEDDING·1K CTX· EMBEDDING

Snowflake Arctic Embed L0.335B

EMBEDDING·1K CTX· EMBEDDING

LFM·125K CTX· CHAT· TOOL_USE

GPT-2 Medium 345M0.38B

SMOLLM·8K CTX· CHAT· VISION

FALCON·128K CTX· CHAT

EMBEDDING·8K CTX· EMBEDDING

Snowflake Arctic Embed L v2.00.568B

EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL

Qwen3-Embedding 0.6B0.6B

EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL

Falcon-H1R Tiny 0.6B0.6B

FALCON·32K CTX· CHAT· REASONING

Falcon Perception 0.6B0.6B

FALCON·4K CTX· VISION

LFM·125K CTX· CHAT· TOOL_USE

QWEN·32K CTX· CHAT· REASONING

GPT-2 Large 774M0.81B

QWEN·256K CTX· CHAT· CODING· MULTILINGUAL

OTHER·32K CTX· CHAT· VISION

MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL

LFM2.5-1.2B-Thinking1.2B

LFM·122K CTX· CHAT· REASONING· TOOL_USE

LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL

OTHER·256K CTX· CHAT· VISION

DeepSeek Coder 1.3B1.35B

DEEPSEEK·16K CTX· CODING

PHI·2K CTX· CHAT· CODING

LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL

▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your GRID A100B.

▸Find models for GRID A100B Compare with other GPUs

WHAT THIS CARD IS WORTH

GRID A100B holds 345 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is DeepSeek R1 Distill Llama 70B at IQ4_XS.

TOKENS/SEC PER $100

—

8B at Q4_K_M, so cards compare like for like

VRAM PER $100

—

what memory costs on this card

THE BIGGEST IT TAKES

DeepSeek R1 Distill Llama 70B70.6B · IQ4_XS43.1 GB19 tok/sEST

Llama 3.3 70B70.6B · IQ4_XS43.1 GB19 tok/sEST

Llama 3.1 70B70.6B · IQ4_XS43.1 GB19 tok/sEST

Llama 3 70B70.6B · IQ4_XS43.1 GB19 tok/sEST

Llama-3.1-Nemotron-70B70.6B · IQ4_XS43.1 GB19 tok/sEST

Cogito 70B70B · IQ4_XS42.8 GB19 tok/sEST

Llama 2 70B70B · IQ4_XS42.8 GB19 tok/sEST

CodeLlama 70B70B · IQ4_XS42.8 GB19 tok/sEST

AGAINST CARDS OF SIMILAR MEMORY

H100 SXM5 64 GB64 GB$25,0000.2 tok/s per $100

Radeon Instinct MI20064 GB$10,0001.8 tok/s per $100

Radeon Instinct MI21064 GB$8,0002.2 tok/s per $100

M1 Ultra (64GB)48 GB$2,4992.9 tok/s per $100

GRID A100B48 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

NVIDIA GRID A100B — 48 GB VRAM.

▸ GRID A100B SPEC

BRAND: NVIDIA
VRAM: 48 GB HBM2e
BANDWIDTH: 1870 GB/s
FP16 COMPUTE: 55.6 TFLOPS
FP32 COMPUTE: 13.9 TFLOPS
CUDA CORES: 6,912
TENSOR CORES: 432
TDP: 400 W
ARCHITECTURE: Ampere

▸ AI CAPABILITY

345/ 449 models @ Q4

With 48 GB VRAM and 1870 GB/s bandwidth, this GPU handles models up to 65.2B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~214 tok/s.

RENT IT — LIVE PRICES

Checking what the clouds are charging…

§ 01TOP MODELS FOR GRID A100B

345 FIT · SHOWING 20

MODEL	SIZE	VRAM Q4	TOK/S	AVG
LLaMA 1 65B	65.2B	40.3 GB	23	42.6
Jamba 2 Mini	52B	32.3 GB	125	9.2
Jamba 1.5 Mini 52B	51.6B	32.0 GB	125	24.2
Kimi-Linear-48B-A3B	48B	29.8 GB	499	26.6
Nemotron-H 47B	47B	29.2 GB	32	84.6
Mixtral-8x7B	46.7B	29.0 GB	115	18.8
Nous-Hermes-2-Mixtral-8x7B-DPO	46.7B	29.0 GB	115	27.4
Dolphin 2.6 Mixtral 8x7B	46.7B	29.0 GB	115	23.8
Phi-3.5 MoE 42B	41.9B	26.1 GB	227	56.7
Falcon 40B	40B	24.9 GB	37	20.9
InternVL3 38B	38B	23.7 GB	39	78.9
Seed-OSS 36B Instruct	36B	22.5 GB	42	54.4
c4ai-command-r-v01 35B	35B	21.9 GB	43	27.5
Qwen 3.5 35B A3B	35B	21.9 GB	499	53.3
Qwen 3.6 35B A3B	35B	21.9 GB	499	53.9
Nous Capybara 34B	34.4B	21.5 GB	43	42.0
Yi-1.5 34B	34.4B	21.5 GB	43	45.3
Falcon-H1 34B	34B	21.3 GB	44	66.1
CodeLlama 34B	34B	21.3 GB	44	25.4
Nous Hermes 2 34B	34B	21.3 GB	44	47.0