FitMyLLM
NVIDIA· Pascal

NVIDIA GeForce GTX 1050 Mobile 3 GB

Running LLMs on the GeForce GTX 1050 Mobile 3 GB — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
3 GB
Budget
Bandwidth
84
GB/s
Models Q4
87/498
17%
7B Q4 speed
~10
Usable
Model coverage at Q417% of all
Estimated speed· By model size at Q4

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

3B
~22
tok/s
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
3 GB
Bandwidth
84 GB/s
FP16 Compute
2.2 TFLOPS
TDP
75W
Memory
GDDR5
Architecture
Pascal
CUDA Cores
768
PCIe
Gen 3 x16
64
Fast models · >30 tok/s
Real-time chat speed
87
Usable · >10 tok/s
Comfortable for all tasks
87
Total compatible
Fit in VRAM at Q4
Don’t want to buy?

Test GeForce GTX 1050 Mobile 3 GB (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· 87
S
Falcon-H1R Tiny 90M0.09B
Falcon·256K ctx· chat· reasoning
747
tok/s · 18% VRAM
›
S
SmolLM2 135M0.135B
Smollm·2K ctx· chat
498
tok/s · 19% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
Embedding·8K ctx· chat
480
tok/s · 19% VRAM
›
S
GPT-2 124M0.14B
Gpt2·1K ctx· chat
480
tok/s · 19% VRAM
›
S
SmolVLM 256M0.256B
Smollm·8K ctx· chat· vision
263
tok/s · 21% VRAM
›
S
Gemma 3 270M0.27B
Gemma·32K ctx· chat
249
tok/s · 22% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
Embedding·8K ctx· embedding· multilingual
220
tok/s · 22% VRAM
›
S
bge-large-en-v1.5 335M0.335B
Embedding·1K ctx· chat
201
tok/s · 23% VRAM
›
S
mxbai-embed-large-v10.335B
Embedding·1K ctx· embedding
201
tok/s · 23% VRAM
›
S
Snowflake Arctic Embed L0.335B
Embedding·1K ctx· embedding
201
tok/s · 23% VRAM
›
S
LFM2 350M0.35B
Lfm·125K ctx· chat· tool_use
192
tok/s · 23% VRAM
›
S
SmolLM2 360M0.36B
Smollm·8K ctx· chat
187
tok/s · 24% VRAM
›
S
GPT-2 Medium 345M0.38B
Gpt2·1K ctx· chat
177
tok/s · 24% VRAM
›
S
Qwen 2.5 0.5B0.5B
Qwen·32K ctx· chat
134
tok/s · 26% VRAM
›
S
SmolVLM 500M0.5B
Smollm·8K ctx· chat· vision
134
tok/s · 26% VRAM
›
S
Falcon-H1 0.5B0.52B
Falcon·128K ctx· chat
129
tok/s · 27% VRAM
›
S
BGE-M30.568B
Embedding·8K ctx· embedding
118
tok/s · 28% VRAM
›
S
Snowflake Arctic Embed L v2.00.568B
Embedding·8K ctx· embedding· multilingual
118
tok/s · 28% VRAM
›
S
Qwen3-Embedding 0.6B0.6B
Embedding·32K ctx· embedding· multilingual
112
tok/s · 29% VRAM
›
S
Falcon-H1R Tiny 0.6B0.6B
Falcon·32K ctx· chat· reasoning
112
tok/s · 29% VRAM
›
S
Falcon Perception 0.6B0.6B
Falcon·4K ctx· vision
112
tok/s · 29% VRAM
›
S
Qwen 1.5 0.5B0.62B
Qwen·32K ctx· chat
108
tok/s · 29% VRAM
›
S
LFM2 700M0.74B
Lfm·125K ctx· chat· tool_use
91
tok/s · 31% VRAM
›
S
Qwen3 0.6B0.75B
Qwen·32K ctx· chat· reasoning
90
tok/s · 32% VRAM
›
S
GPT-2 Large 774M0.81B
Gpt2·1K ctx· chat
83
tok/s · 33% VRAM
›
S
Qwen 3.5 0.8B0.87B
Qwen·256K ctx· chat· coding· multilingual
77
tok/s · 34% VRAM
›
S
InternVL3 1B0.94B
Other·32K ctx· chat· vision
71
tok/s · 35% VRAM
›
S
MiniCPM5 1B1.08B
Minicpm·128K ctx· chat· reasoning· multilingual
62
tok/s · 38% VRAM
›
S
K2 Horizon 0.9B1.08B
Other·128K ctx· chat· coding· reasoning
62
tok/s · 38% VRAM
›
S
TinyLlama 1.1B1.1B
Llama·2K ctx· chat
61
tok/s · 39% VRAM
›
A
LFM2.5-1.2B-Thinking1.2B
Lfm·122K ctx· chat· reasoning· tool_use
56
tok/s · 41% VRAM
›
A
Llama-3.2-1B1.2B
Llama·4K ctx· chat
56
tok/s · 41% VRAM
›
A
LFM2 1.2B1.2B
Lfm·125K ctx· chat· tool_use· multilingual
56
tok/s · 41% VRAM
›
A
Zamba2 1.2B1.2B
Other·4K ctx· chat
56
tok/s · 41% VRAM
›
A
EXAONE-4.0-1.2B1.3B
Exaone·64K ctx· chat
52
tok/s · 43% VRAM
›
A
OPT 1.3B1.3B
Opt·2K ctx· chat
52
tok/s · 43% VRAM
›
A
MiniCPM-V 4.61.3B
Other·256K ctx· chat· vision
52
tok/s · 43% VRAM
›
A
DeepSeek Coder 1.3B1.35B
Deepseek·16K ctx· coding
50
tok/s · 44% VRAM
›
A
Phi-1 1.3B1.42B
Phi·2K ctx· coding
47
tok/s · 45% VRAM
›
A
Phi-1.5 1.3B1.42B
Phi·2K ctx· chat· coding
47
tok/s · 45% VRAM
›
Next step

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce GTX 1050 Mobile 3 GB.

What this card is worth

GTX 1050 Mobile 3 GB holds 87 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is Falcon3-3B 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
Falcon3-3B3.23B · Q4_K_M2.6 GB32 tok/sest
granite-4.0-h-micro 3.2B3.2B · Q5_K_M2.6 GB28 tok/sest
Llama-3.2-3B3.2B · Q4_K_M2.7 GB32 tok/sest
Falcon-H1 3B3.15B · Q5_K_M2.7 GB28 tok/sest
Qwen 2.5 3B3.1B · Q5_K_M2.6 GB29 tok/sest
SmolLM3-3B3.1B · Q4_K_M2.5 GB33 tok/sest
Ministral 3B3B · Q4_K_M2.6 GB34 tok/sest
StarCoder2 3B3B · Q5_K_M2.5 GB29 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
RTX 2060 6GB6 GB$15026.7 tok/s per $100
GTX 1050 Mobile 3 GB3 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 GTX 1050 Mobile 3 GB — 3 GB VRAM.

GeForce GTX 1050 Mobile 3 GB spec
Brand
NVIDIA
VRAM
3 GB GDDR5
Bandwidth
84 GB/s
FP16 Compute
2.2 TFLOPS
FP32 Compute
2.2 TFLOPS
CUDA Cores
768
TDP
75 W
Architecture
Pascal
AI capability
87/ 498 models @ Q4

With 3 GB VRAM and 84 GB/s bandwidth, this GPU handles models up to 3.1B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~10 tok/s.

Top models for GeForce GTX 1050 Mobile 3 GB
87 fit · showing 20
ModelSizeVRAM Q4tok/sAvg
Qwen 2.5 3B3.1B2.4 GB2237.2
SmolLM3-3B3.1B2.4 GB2235.1
Ministral 3B3B2.3 GB2223.7
StarCoder2 3B3B2.3 GB229.5
Granite 4.1 3B3B2.3 GB2217.5
xLAM-2 3B Function-Calling3B2.3 GB22—
Jamba 2 3B3B2.3 GB22—
Dolly v2 3B2.8B2.2 GB245.6
StableLM Zephyr 3B2.79B2.2 GB2414.9
Zephyr 3B2.79B2.2 GB2414.4
OPT 2.7B2.7B2.1 GB2528.0
Phi-2 2.7B2.7B2.1 GB2524.1
Zamba2 2.7B2.7B2.1 GB2548.0
LFM2.5 2.6B2.7B2.1 GB2528.3
Granite 3.0 2B2.63B2.1 GB2635.8
gemma-2-2b2.6B2.1 GB2622.9
LFM2 2.6B2.6B2.1 GB2616.3
Granite 3.1 2B2.53B2.0 GB2737.8
Granite 3.3 2B2.53B2.0 GB2720.5
MiniCPM5 2B2.52B2.0 GB2749.2