▸ NVIDIA· FERMI 2.0

NVIDIA NVS 4200M

VRAM

1 GB

BUDGET

BANDWIDTH

12.8

GB/S

MODELS Q4

13/331

4%

7B Q4 SPEED

~1

SLOW

▸ MODEL COVERAGE @ Q44% OF ALL

▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B

—

1.7GB NEEDED

7B

—

3.9GB NEEDED

14B

—

7.9GB NEEDED

32B

—

18.0GB NEEDED

70B

—

39.4GB NEEDED

▸ SPECIFICATIONS

VRAM

1 GB

BANDWIDTH

12.8 GB/s

FP16 COMPUTE

0.2 TFLOPS

TDP

25W

MEMORY

DDR3

ARCHITECTURE

Fermi 2.0

CUDA CORES

48

7

FAST MODELS · >30 TOK/S

Real-time chat speed

13

USABLE · >10 TOK/S

Comfortable for all tasks

13

TOTAL COMPATIBLE

Fit in VRAM at Q4

▸ DON’T WANT TO BUY?

Test NVS 4200M (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· 13

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

EMBEDDING·8K CTX· CHAT

TOK/S · 55% VRAM

GPT-2 124M0.124B

GPT2·1K CTX· CHAT

TOK/S · 56% VRAM

SmolLM2 135M0.135B

SMOLLM·2K CTX· CHAT

TOK/S · 57% VRAM

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

EMBEDDING·1K CTX· CHAT

TOK/S · 69% VRAM

mxbai-embed-large-v10.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 69% VRAM

Snowflake Arctic Embed L0.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 69% VRAM

GPT-2 Medium 345M0.345B

GPT2·1K CTX· CHAT

TOK/S · 70% VRAM

SmolLM2 360M0.36B

SMOLLM·8K CTX· CHAT

TOK/S · 71% VRAM

Falcon-H1 0.5B0.5B

FALCON·128K CTX· CHAT

TOK/S · 79% VRAM

Qwen 1.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 79% VRAM

Qwen 2.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 79% VRAM

EMBEDDING·8K CTX· EMBEDDING

TOK/S · 84% VRAM

QWEN·32K CTX· CHAT· REASONING

TOK/S · 86% VRAM

▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your NVS 4200M.

▸Find models for NVS 4200M Compare with other GPUs

▸ DEVICE UNDER TEST

NVIDIA NVS 4200M — 1 GB VRAM.

▸ NVS 4200M SPEC

BRAND: NVIDIA
VRAM: 1 GB DDR3
BANDWIDTH: 12.8 GB/s
FP16 COMPUTE: 0.2 TFLOPS
FP32 COMPUTE: 0.2 TFLOPS
CUDA CORES: 48
TDP: 25 W
ARCHITECTURE: Fermi 2.0

▸ AI CAPABILITY

13/ 331 models @ Q4

With 1 GB VRAM and 12.8 GB/s bandwidth, this GPU handles models up to 0.6B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~1 tok/s.

§ 01TOP MODELS FOR NVS 4200M

13 FIT · SHOWING 13

MODEL	SIZE	VRAM Q4	TOK/S	AVG
Qwen3 0.6B	0.6B	0.9 GB	17	19.1
BGE-M3	0.568B	0.8 GB	18	63.0
Falcon-H1 0.5B	0.5B	0.8 GB	20	41.7
Qwen 1.5 0.5B	0.5B	0.8 GB	20	9.9
Qwen 2.5 0.5B	0.5B	0.8 GB	20	19.4
SmolLM2 360M	0.36B	0.7 GB	28	8.2
GPT-2 Medium 345M	0.345B	0.7 GB	30	5.9
bge-large-en-v1.5 335M	0.335B	0.7 GB	31	62.3
mxbai-embed-large-v1	0.335B	0.7 GB	31	64.7
Snowflake Arctic Embed L	0.335B	0.7 GB	31	56.0
SmolLM2 135M	0.135B	0.6 GB	76	7.0
GPT-2 124M	0.124B	0.6 GB	83	6.5
nomic-embed-text-v1.5 100M	0.1B	0.5 GB	102	62.3