▸ NVIDIA· FERMI

NVIDIA Quadro 4000M

VRAM

2 GB

BUDGET

BANDWIDTH

80

GB/S

MODELS Q4

62/428

14%

7B Q4 SPEED

~9

USABLE

▸ MODEL COVERAGE @ Q414% OF ALL

▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B

~21

TOK/S

7B

—

3.9GB NEEDED

14B

—

7.9GB NEEDED

32B

—

18.0GB NEEDED

70B

—

39.4GB NEEDED

▸ SPECIFICATIONS

VRAM

2 GB

BANDWIDTH

80 GB/s

FP16 COMPUTE

0.6 TFLOPS

TDP

100W

MEMORY

GDDR5

ARCHITECTURE

Fermi

CUDA CORES

336

62

FAST MODELS · >30 TOK/S

Real-time chat speed

62

USABLE · >10 TOK/S

Comfortable for all tasks

62

TOTAL COMPATIBLE

Fit in VRAM at Q4

▸ DON’T WANT TO BUY?

Test Quadro 4000M (or anything bigger) without committing. Pay by the second, cancel anytime.

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· 62

Falcon-H1R Tiny 90M0.09B

FALCON·256K CTX· CHAT· REASONING

TOK/S · 27% VRAM

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

EMBEDDING·8K CTX· CHAT

TOK/S · 27% VRAM

GPT-2 124M0.124B

GPT2·1K CTX· CHAT

TOK/S · 28% VRAM

SmolLM2 135M0.135B

SMOLLM·2K CTX· CHAT

TOK/S · 29% VRAM

SmolVLM 256M0.256B

SMOLLM·8K CTX· CHAT· VISION

TOK/S · 32% VRAM

Gemma 3 270M0.27B

GEMMA·32K CTX· CHAT

TOK/S · 33% VRAM

Snowflake Arctic Embed M v2.00.305B

EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL

TOK/S · 34% VRAM

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

EMBEDDING·1K CTX· CHAT

TOK/S · 35% VRAM

mxbai-embed-large-v10.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 35% VRAM

Snowflake Arctic Embed L0.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 35% VRAM

GPT-2 Medium 345M0.345B

GPT2·1K CTX· CHAT

TOK/S · 35% VRAM

LFM·125K CTX· CHAT· TOOL_USE

TOK/S · 35% VRAM

SmolLM2 360M0.36B

SMOLLM·8K CTX· CHAT

TOK/S · 35% VRAM

Falcon-H1 0.5B0.5B

FALCON·128K CTX· CHAT

TOK/S · 40% VRAM

Qwen 1.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 40% VRAM

Qwen 2.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 40% VRAM

SmolVLM 500M0.5B

SMOLLM·8K CTX· CHAT· VISION

TOK/S · 40% VRAM

EMBEDDING·8K CTX· EMBEDDING

TOK/S · 42% VRAM

Snowflake Arctic Embed L v2.00.568B

EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL

TOK/S · 42% VRAM

QWEN·32K CTX· CHAT· REASONING

TOK/S · 43% VRAM

Qwen3-Embedding 0.6B0.6B

EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL

TOK/S · 43% VRAM

Falcon-H1R Tiny 0.6B0.6B

FALCON·32K CTX· CHAT· REASONING

TOK/S · 43% VRAM

Falcon Perception 0.6B0.6B

FALCON·4K CTX· VISION

TOK/S · 43% VRAM

LFM·125K CTX· CHAT· TOOL_USE

TOK/S · 46% VRAM

GPT-2 Large 774M0.774B

GPT2·1K CTX· CHAT

TOK/S · 48% VRAM

Qwen 3.5 0.8B0.8B

QWEN·256K CTX· CHAT· CODING· MULTILINGUAL

TOK/S · 49% VRAM

Qwen3.5-0.8B0.9B

QWEN·256K CTX· CHAT

TOK/S · 52% VRAM

FALCON·32K CTX· CHAT

TOK/S · 55% VRAM

INTERNLM·32K CTX· CHAT

TOK/S · 55% VRAM

OTHER·32K CTX· CHAT· VISION

TOK/S · 55% VRAM

TinyLlama 1.1B1.1B

LLAMA·2K CTX· CHAT

TOK/S · 58% VRAM

LFM2.5-1.2B-Thinking1.2B

LFM·122K CTX· CHAT· REASONING· TOOL_USE

TOK/S · 61% VRAM

Llama-3.2-1B1.2B

LLAMA·4K CTX· CHAT

TOK/S · 61% VRAM

LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL

TOK/S · 61% VRAM

Zamba2 1.2B1.2B

OTHER·4K CTX· CHAT

TOK/S · 61% VRAM

DeepSeek Coder 1.3B1.3B

DEEPSEEK·16K CTX· CODING

TOK/S · 64% VRAM

EXAONE-4.0-1.2B1.3B

EXAONE·64K CTX· CHAT

TOK/S · 64% VRAM

OPT·2K CTX· CHAT

TOK/S · 64% VRAM

PHI·2K CTX· CODING

TOK/S · 64% VRAM

Phi-1.5 1.3B1.3B

PHI·2K CTX· CHAT· CODING

TOK/S · 64% VRAM

▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Quadro 4000M.

▸Find models for Quadro 4000M Compare with other GPUs

▸ DEVICE UNDER TEST

NVIDIA Quadro 4000M — 2 GB VRAM.

▸ QUADRO 4000M SPEC

BRAND: NVIDIA
VRAM: 2 GB GDDR5
BANDWIDTH: 80 GB/s
FP16 COMPUTE: 0.6 TFLOPS
FP32 COMPUTE: 0.6 TFLOPS
CUDA CORES: 336
TDP: 100 W
ARCHITECTURE: Fermi

▸ AI CAPABILITY

62/ 428 models @ Q4

With 2 GB VRAM and 80 GB/s bandwidth, this GPU handles models up to 2B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~9 tok/s.

§ 01TOP MODELS FOR QUADRO 4000M

62 FIT · SHOWING 20

MODEL	SIZE	VRAM Q4	TOK/S	AVG
Gemma 1 2B	2B	1.7 GB	32	20.2
Granite 3.0 2B	2B	1.7 GB	32	35.8
Granite 3.1 2B	2B	1.7 GB	32	37.8
Granite 3.3 2B	2B	1.7 GB	32	20.5
Qwen 3.5 2B	2B	1.7 GB	32	29.7
Qwen3-VL 2B Instruct	2B	1.7 GB	32	18.4
InternVL3 2B	2B	1.7 GB	32	64.9
Moondream2 1.9B	1.9B	1.6 GB	34	26.2
Qwen 1.5 1.8B	1.8B	1.6 GB	36	19.6
SmolLM2 1.7B	1.71B	1.5 GB	37	16.2
Qwen3 1.7B	1.7B	1.5 GB	38	30.1
stablelm-2-1_6b	1.6B	1.5 GB	40	9.5
LFM2-VL 1.6B	1.6B	1.5 GB	40	39.7
Falcon-H1 1.5B	1.5B	1.4 GB	43	43.8
GPT-2 XL 1.5B	1.5B	1.4 GB	43	5.1
Qwen2.5-Coder-1.5B	1.5B	1.4 GB	43	19.6
Qwen2 Math 1.5B	1.5B	1.4 GB	43	19.6
Qwen 2.5 1.5B	1.5B	1.4 GB	43	30.2
Yi Coder 1.5B	1.5B	1.4 GB	43	14.6
Stella en 1.5B v5	1.5B	1.4 GB	43	—