FitMyLLM
▸ NVIDIA· FERMI 2.0

NVIDIA GeForce GT 520 PCIe x1

Running LLMs on the GeForce GT 520 PCIe x1 — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
1 GB
BUDGET
BANDWIDTH
14.4
GB/S
MODELS Q4
4/449
1%
7B Q4 SPEED
~2
SLOW
▸ MODEL COVERAGE @ Q41% 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
▸ 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
1 GB
BANDWIDTH
14.4 GB/s
FP16 COMPUTE
0.2 TFLOPS
TDP
29W
MEMORY
DDR3
ARCHITECTURE
Fermi 2.0
CUDA CORES
48
PCIE
Gen 2 x16
4
FAST MODELS · >30 TOK/S
Real-time chat speed
4
USABLE · >10 TOK/S
Comfortable for all tasks
4
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test GeForce GT 520 PCIe x1 (or anything bigger) without committing. Pay by the second, cancel anytime.

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· 4
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
128
TOK/S · 54% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
85
TOK/S · 57% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
82
TOK/S · 57% VRAM
›
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
82
TOK/S · 57% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce GT 520 PCIe x1.

WHAT THIS CARD IS WORTH

GT 520 PCIe x1 holds 4 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is Qwen 3.5 0.8B at Q4_K_M.

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
Qwen 3.5 0.8B0.87B · Q4_K_M0.9 GB20 tok/sEST
LFM2 700M0.74B · Q4_K_M0.9 GB24 tok/sEST
Falcon-H1R Tiny 0.6B0.6B · Q6_K0.9 GB22 tok/sEST
Falcon Perception 0.6B0.6B · Q5_K_S0.9 GB26 tok/sEST
Falcon-H1 0.5B0.52B · Q6_K0.8 GB25 tok/sEST
Qwen 2.5 0.5B0.5B · Q8_00.9 GB20 tok/sEST
SmolVLM 500M0.5B · Q6_K0.9 GB26 tok/sEST
SmolLM2 360M0.36B · Q8_00.8 GB28 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M2 (8GB)5 GB$5992.8 tok/s per $100
M3 (8GB)5 GB$5992.8 tok/s per $100
M1 (8GB)5 GB$4992.2 tok/s per $100
Radeon RX 6600S4 GB$175—
GT 520 PCIe x11 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 GeForce GT 520 PCIe x1 — 1 GB VRAM.

▸ GEFORCE GT 520 PCIE X1 SPEC
BRAND
NVIDIA
VRAM
1 GB DDR3
BANDWIDTH
14.4 GB/s
FP16 COMPUTE
0.2 TFLOPS
FP32 COMPUTE
0.2 TFLOPS
CUDA CORES
48
TDP
29 W
ARCHITECTURE
Fermi 2.0
▸ AI CAPABILITY
4/ 449 models @ Q4

With 1 GB VRAM and 14.4 GB/s bandwidth, this GPU handles models up to 0.14B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~2 tok/s.

§ 01TOP MODELS FOR GEFORCE GT 520 PCIE X1
4 FIT · SHOWING 4
MODELSIZEVRAM Q4TOK/SAVG
nomic-embed-text-v1.5 100M0.14B0.6 GB8262.3
GPT-2 124M0.14B0.6 GB826.5
SmolLM2 135M0.135B0.6 GB857.0
Falcon-H1R Tiny 90M0.09B0.5 GB128—