FitMyLLM
NVIDIA· AMPERE

NVIDIA GeForce RTX 3050 A Mobile

Running LLMs on the GeForce RTX 3050 A Mobile — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
4 GB
BUDGET
BANDWIDTH
192
GB/S
MODELS Q4
97/449
22%
7B Q4 SPEED
~22
GOOD
▸ 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
~51
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
4 GB
BANDWIDTH
192 GB/s
FP16 COMPUTE
4.8 TFLOPS
TDP
45W
MEMORY
GDDR6
ARCHITECTURE
Ampere
CUDA CORES
1,792
TENSOR CORES
56
PCIE
Gen 4 x8
97
FAST MODELS · >30 TOK/S
Real-time chat speed
97
USABLE · >10 TOK/S
Comfortable for all tasks
97
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test GeForce RTX 3050 A Mobile (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· 97
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
1707
TOK/S · 14% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
1138
TOK/S · 14% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
1097
TOK/S · 14% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
1097
TOK/S · 14% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
600
TOK/S · 16% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
569
TOK/S · 16% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
504
TOK/S · 17% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
459
TOK/S · 17% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
459
TOK/S · 17% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
459
TOK/S · 17% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
439
TOK/S · 18% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
427
TOK/S · 18% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
404
TOK/S · 18% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
307
TOK/S · 20% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
307
TOK/S · 20% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
295
TOK/S · 20% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
270
TOK/S · 21% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
270
TOK/S · 21% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
256
TOK/S · 21% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
256
TOK/S · 21% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
256
TOK/S · 21% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
248
TOK/S · 22% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
208
TOK/S · 24% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
205
TOK/S · 24% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
190
TOK/S · 25% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
177
TOK/S · 26% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
163
TOK/S · 27% VRAM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
142
TOK/S · 29% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
140
TOK/S · 29% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
128
TOK/S · 31% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
128
TOK/S · 31% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
128
TOK/S · 31% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
128
TOK/S · 31% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
118
TOK/S · 32% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
118
TOK/S · 32% VRAM
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
118
TOK/S · 32% VRAM
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
114
TOK/S · 33% VRAM
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
108
TOK/S · 34% VRAM
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
108
TOK/S · 34% VRAM
S
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
102
TOK/S · 35% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your GeForce RTX 3050 A Mobile.

WHAT THIS CARD IS WORTH

RTX 3050 A Mobile holds 97 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is InternLM2 5B 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
InternLM2 5B4.5B · Q4_K_M3.6 GB43 tok/sEST
Ministral 3 3B Reasoning4.25B · Q4_K_M3.3 GB45 tok/sEST
Qwen3 4B4B · Q4_K_M3.3 GB48 tok/sEST
Qwen3-4B Instruct 25074B · Q4_K_M3.3 GB48 tok/sEST
Qwen3-Embedding 4B4B · Q4_K_M3.3 GB48 tok/sEST
Nemotron 3 Nano 4B3.97B · Q4_K_M3.4 GB48 tok/sEST
Ministral 3 3B3.85B · Q5_K_M3.5 GB43 tok/sEST
phi-3-mini-4k 3.8B3.8B · Q4_K_M3.4 GB50 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
RTX 3070 Ti8 GB$49912.6 tok/s per $100
RTX 3060 Ti GDDR6X8 GB$39915.8 tok/s per $100
RTX 3070 Ti 8 GB GA1028 GB$59910.5 tok/s per $100
Arc A7508 GB$19910.1 tok/s per $100
RTX 3050 A Mobile4 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 RTX 3050 A Mobile — 4 GB VRAM.

GEFORCE RTX 3050 A MOBILE SPEC
BRAND
NVIDIA
VRAM
4 GB GDDR6
BANDWIDTH
192 GB/s
FP16 COMPUTE
4.8 TFLOPS
FP32 COMPUTE
4.8 TFLOPS
CUDA CORES
1,792
TENSOR CORES
56
TDP
45 W
ARCHITECTURE
Ampere
▸ AI CAPABILITY
97/ 449 models @ Q4

With 4 GB VRAM and 192 GB/s bandwidth, this GPU handles models up to 4.25B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~22 tok/s.

§ 01TOP MODELS FOR GEFORCE RTX 3050 A MOBILE
97 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Ministral 3 3B Reasoning4.25B3.1 GB36
Qwen 1.5 4B4B2.9 GB3812.6
Qwen3 4B4B2.9 GB3840.7
Qwen3-4B Instruct 25074B2.9 GB3837.2
Qwen3-Embedding 4B4B2.9 GB38
Nemotron 3 Nano 4B3.97B2.9 GB3932.0
Ministral 3 3B3.85B2.8 GB4021.4
Phi-3.5 Mini 3.8B3.82B2.8 GB4046.6
phi-3-mini-4k 3.8B3.8B2.8 GB4030.5
Phi-4-mini 3.8B3.8B2.8 GB4049.0
Cogito 3B3.61B2.7 GB4322.1
Falcon3-3B3.23B2.5 GB4825.7
granite-4.0-h-micro 3.2B3.2B2.4 GB4818.4
Llama-3.2-3B3.2B2.4 GB4817.9
Falcon-H1 3B3.15B2.4 GB4949.5
Qwen 2.5 3B3.1B2.4 GB5037.2
SmolLM3-3B3.1B2.4 GB5030.5
Ministral 3B3B2.3 GB5129.6
StarCoder2 3B3B2.3 GB519.5
Granite 4.1 3B3B2.3 GB5116.6