NVIDIA· MAXWELL

NVIDIA GeForce GTX 745 OEM

VRAM
4 GB
BUDGET
BANDWIDTH
29
GB/S
MODELS Q4
74/331
22%
7B Q4 SPEED
~3
SLOW
▸ MODEL COVERAGE @ Q422% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~8
TOK/S
7B
3.9GB NEEDED
14B
7.9GB NEEDED
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
4 GB
BANDWIDTH
29 GB/s
FP16 COMPUTE
0.8 TFLOPS
TDP
55W
MEMORY
DDR3
ARCHITECTURE
Maxwell
CUDA CORES
384
PCIE
Gen 3 x16
14
FAST MODELS · >30 TOK/S
Real-time chat speed
45
USABLE · >10 TOK/S
Comfortable for all tasks
74
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test GeForce GTX 745 OEM (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· 74
S
nomic-embed-text-v1.5 100M0.1B
EMBEDDING·8K CTX· CHAT
232
TOK/S · 14% VRAM
S
GPT-2 124M0.124B
GPT2·1K CTX· CHAT
187
TOK/S · 14% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
172
TOK/S · 14% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
69
TOK/S · 17% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
69
TOK/S · 17% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
69
TOK/S · 17% VRAM
S
GPT-2 Medium 345M0.345B
GPT2·1K CTX· CHAT
67
TOK/S · 17% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
64
TOK/S · 18% VRAM
A
Falcon-H1 0.5B0.5B
FALCON·128K CTX· CHAT
46
TOK/S · 20% VRAM
A
Qwen 1.5 0.5B0.5B
QWEN·32K CTX· CHAT
46
TOK/S · 20% VRAM
A
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
46
TOK/S · 20% VRAM
A
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
41
TOK/S · 21% VRAM
B
Qwen3 0.6B0.6B
QWEN·32K CTX· CHAT· REASONING
39
TOK/S · 21% VRAM
B
GPT-2 Large 774M0.774B
GPT2·1K CTX· CHAT
30
TOK/S · 24% VRAM
B
Qwen 3.5 0.8B0.8B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
29
TOK/S · 24% VRAM
B
Qwen3.5-0.8B0.9B
QWEN·256K CTX· CHAT
26
TOK/S · 26% VRAM
C
Falcon3-1B1B
FALCON·32K CTX· CHAT
23
TOK/S · 27% VRAM
C
InternLM2 1B1B
INTERNLM·32K CTX· CHAT
23
TOK/S · 27% VRAM
C
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
21
TOK/S · 29% VRAM
C
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
19
TOK/S · 31% VRAM
C
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
19
TOK/S · 31% VRAM
C
DeepSeek Coder 1.3B1.3B
DEEPSEEK·16K CTX· CODING
18
TOK/S · 32% VRAM
C
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
18
TOK/S · 32% VRAM
C
OPT 1.3B1.3B
OPT·2K CTX· CHAT
18
TOK/S · 32% VRAM
C
Phi-1 1.3B1.3B
PHI·2K CTX· CODING
18
TOK/S · 32% VRAM
C
Phi-1.5 1.3B1.3B
PHI·2K CTX· CHAT· CODING
18
TOK/S · 32% VRAM
C
stablelm-2-1_6b1.6B
STABLELM·4K CTX· CHAT
15
TOK/S · 37% VRAM
C
Falcon-H1 1.5B1.5B
FALCON·128K CTX· CHAT· CODING
15
TOK/S · 35% VRAM
C
GPT-2 XL 1.5B1.5B
GPT2·1K CTX· CHAT
15
TOK/S · 35% VRAM
C
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
15
TOK/S · 35% VRAM
C
Qwen2 Math 1.5B1.5B
QWEN·4K CTX· REASONING
15
TOK/S · 35% VRAM
C
Qwen 2.5 1.5B1.5B
QWEN·32K CTX· CHAT· CODING
15
TOK/S · 35% VRAM
C
Yi Coder 1.5B1.5B
YI·125K CTX· CODING
15
TOK/S · 35% VRAM
D
SmolLM2 1.7B1.71B
SMOLLM·8K CTX· CHAT
14
TOK/S · 38% VRAM
D
Qwen3 1.7B1.7B
QWEN·32K CTX· CHAT· REASONING
14
TOK/S · 38% VRAM
D
Qwen 1.5 1.8B1.8B
QWEN·32K CTX· CHAT
13
TOK/S · 40% VRAM
D
Gemma 1 2B2B
GEMMA·8K CTX· CHAT
12
TOK/S · 43% VRAM
D
Granite 3.0 2B2B
GRANITE·128K CTX· CHAT· CODING
12
TOK/S · 43% VRAM
D
Granite 3.1 2B2B
GRANITE·128K CTX· CHAT· CODING
12
TOK/S · 43% VRAM
D
Granite 3.3 2B2B
GRANITE·125K CTX· CHAT· REASONING· CODING
12
TOK/S · 43% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce GTX 745 OEM.

▸ DEVICE UNDER TEST

NVIDIA GeForce GTX 745 OEM4 GB VRAM.

GEFORCE GTX 745 OEM SPEC
BRAND
NVIDIA
VRAM
4 GB DDR3
BANDWIDTH
29 GB/s
FP16 COMPUTE
0.8 TFLOPS
FP32 COMPUTE
0.8 TFLOPS
CUDA CORES
384
TDP
55 W
ARCHITECTURE
Maxwell
▸ AI CAPABILITY
74/ 331 models @ Q4

With 4 GB VRAM and 29 GB/s bandwidth, this GPU handles models up to 4.7B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~3 tok/s.

§ 01TOP MODELS FOR GEFORCE GTX 745 OEM
74 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Qwen3.5-4B4.7B3.4 GB529.3
InternLM2 5B4.5B3.2 GB547.6
Gemma 3 4B4.3B3.1 GB522.8
TranslateGemma 4B4B2.9 GB65.5
MedGemma 1.5 4B4B2.9 GB65.5
Qwen 1.5 4B4B2.9 GB612.6
Qwen3 4B4B2.9 GB640.7
Qwen 3.5 4B4B2.9 GB647.4
Nemotron 3 Nano 4B3.97B2.9 GB632.0
Phi-3.5 Mini 3.8B3.82B2.8 GB646.6
phi-3-mini-4k 3.8B3.8B2.8 GB630.5
Phi-4-mini 3.8B3.8B2.8 GB649.0
Qwen2.5-VL-3B3.8B2.8 GB629.9
granite-4.0-h-micro 3.2B3.2B2.4 GB718.4
Llama-3.2-3B3.2B2.4 GB717.9
Falcon3-3B3.1B2.4 GB725.7
Qwen 2.5 3B3.1B2.4 GB737.2
SmolLM3-3B3.1B2.4 GB730.5
Cogito 3B3B2.3 GB822.1
Falcon-H1 3B3B2.3 GB849.5