FitMyLLM
NVIDIA· Pascal

NVIDIA Quadro P4200 Max-Q

Running LLMs on the Quadro P4200 Max-Q — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
8 GB
Entry-level
Bandwidth
224.4
GB/s
Models Q4
214/498
43%
7B Q4 speed
~26
Good
Model coverage at Q443% of all
Estimated speed· By model size at Q4

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

3B
~60
tok/s
7B
~26
tok/s
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
8 GB
Bandwidth
224.4 GB/s
FP16 Compute
0.1 TFLOPS
TDP
100W
Memory
GDDR5
Architecture
Pascal
CUDA Cores
2,304
123
Fast models · >30 tok/s
Real-time chat speed
214
Usable · >10 tok/s
Comfortable for all tasks
214
Total compatible
Fit in VRAM at Q4
Don’t want to buy?

Test Quadro P4200 Max-Q (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· 214
S
Falcon-H1R Tiny 90M0.09B
Falcon·256K ctx· chat· reasoning
1995
tok/s · 7% VRAM
›
S
SmolLM2 135M0.135B
Smollm·2K ctx· chat
1330
tok/s · 7% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
Embedding·8K ctx· chat
1282
tok/s · 7% VRAM
›
S
GPT-2 124M0.14B
Gpt2·1K ctx· chat
1282
tok/s · 7% VRAM
›
S
SmolVLM 256M0.256B
Smollm·8K ctx· chat· vision
701
tok/s · 8% VRAM
›
S
Gemma 3 270M0.27B
Gemma·32K ctx· chat
665
tok/s · 8% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
Embedding·8K ctx· embedding· multilingual
589
tok/s · 8% VRAM
›
S
bge-large-en-v1.5 335M0.335B
Embedding·1K ctx· chat
536
tok/s · 9% VRAM
›
S
mxbai-embed-large-v10.335B
Embedding·1K ctx· embedding
536
tok/s · 9% VRAM
›
S
Snowflake Arctic Embed L0.335B
Embedding·1K ctx· embedding
536
tok/s · 9% VRAM
›
S
LFM2 350M0.35B
Lfm·125K ctx· chat· tool_use
513
tok/s · 9% VRAM
›
S
SmolLM2 360M0.36B
Smollm·8K ctx· chat
499
tok/s · 9% VRAM
›
S
GPT-2 Medium 345M0.38B
Gpt2·1K ctx· chat
472
tok/s · 9% VRAM
›
S
Qwen 2.5 0.5B0.5B
Qwen·32K ctx· chat
359
tok/s · 10% VRAM
›
S
SmolVLM 500M0.5B
Smollm·8K ctx· chat· vision
359
tok/s · 10% VRAM
›
S
Falcon-H1 0.5B0.52B
Falcon·128K ctx· chat
345
tok/s · 10% VRAM
›
S
BGE-M30.568B
Embedding·8K ctx· embedding
316
tok/s · 10% VRAM
›
S
Snowflake Arctic Embed L v2.00.568B
Embedding·8K ctx· embedding· multilingual
316
tok/s · 10% VRAM
›
S
Qwen3-Embedding 0.6B0.6B
Embedding·32K ctx· embedding· multilingual
299
tok/s · 11% VRAM
›
S
Falcon-H1R Tiny 0.6B0.6B
Falcon·32K ctx· chat· reasoning
299
tok/s · 11% VRAM
›
S
Falcon Perception 0.6B0.6B
Falcon·4K ctx· vision
299
tok/s · 11% VRAM
›
S
Qwen 1.5 0.5B0.62B
Qwen·32K ctx· chat
290
tok/s · 11% VRAM
›
S
LFM2 700M0.74B
Lfm·125K ctx· chat· tool_use
243
tok/s · 12% VRAM
›
S
Qwen3 0.6B0.75B
Qwen·32K ctx· chat· reasoning
239
tok/s · 12% VRAM
›
S
GPT-2 Large 774M0.81B
Gpt2·1K ctx· chat
222
tok/s · 12% VRAM
›
S
Qwen 3.5 0.8B0.87B
Qwen·256K ctx· chat· coding· multilingual
206
tok/s · 13% VRAM
›
S
InternVL3 1B0.94B
Other·32K ctx· chat· vision
191
tok/s · 13% VRAM
›
S
MiniCPM5 1B1.08B
Minicpm·128K ctx· chat· reasoning· multilingual
166
tok/s · 14% VRAM
›
S
K2 Horizon 0.9B1.08B
Other·128K ctx· chat· coding· reasoning
166
tok/s · 14% VRAM
›
S
TinyLlama 1.1B1.1B
Llama·2K ctx· chat
163
tok/s · 15% VRAM
›
S
LFM2.5-1.2B-Thinking1.2B
Lfm·122K ctx· chat· reasoning· tool_use
150
tok/s · 15% VRAM
›
S
Llama-3.2-1B1.2B
Llama·4K ctx· chat
150
tok/s · 15% VRAM
›
S
LFM2 1.2B1.2B
Lfm·125K ctx· chat· tool_use· multilingual
150
tok/s · 15% VRAM
›
S
Zamba2 1.2B1.2B
Other·4K ctx· chat
150
tok/s · 15% VRAM
›
S
Ling 3.0 Tiny7.89BMoE
Other·128K ctx· chat· coding· reasoning
138
tok/s · 66% VRAM
›
S
EXAONE-4.0-1.2B1.3B
Exaone·64K ctx· chat
138
tok/s · 16% VRAM
›
S
OPT 1.3B1.3B
Opt·2K ctx· chat
138
tok/s · 16% VRAM
›
S
MiniCPM-V 4.61.3B
Other·256K ctx· chat· vision
138
tok/s · 16% VRAM
›
S
DeepSeek Coder 1.3B1.35B
Deepseek·16K ctx· coding
133
tok/s · 16% VRAM
›
S
Phi-1 1.3B1.42B
Phi·2K ctx· coding
126
tok/s · 17% VRAM
›
Next step

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Quadro P4200 Max-Q.

What this card is worth

Quadro P4200 Max-Q holds 214 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is Falcon3-10B at IQ4_XS.

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
Falcon3-10B10.3B · IQ4_XS7.1 GB23 tok/sest
Bamba 9B v29.78B · Q4_K_M7.2 GB22 tok/sest
RecurrentGemma 9B9.63B · Q4_K_M6.8 GB22 tok/sest
glm-4-9b9.4B · Q4_K_M6.6 GB23 tok/sest
Yi 1.5 9B9B · Q4_K_M6.5 GB24 tok/sest
Yi Coder 9B9B · Q4_K_M6.5 GB24 tok/sest
K2 Horizon 7B9B · Q4_K_M6.7 GB24 tok/sest
Ministral 3 8B8.92B · Q4_K_M6.6 GB24 tok/sest
Against cards of similar memory
M3 Pro (18GB)12 GB$1,5991.5 tok/s per $100
M1 Pro (16GB)11 GB$9992.9 tok/s per $100
M2 Pro (16GB)11 GB$1,2992.2 tok/s per $100
M4 (16GB)11 GB$4994.0 tok/s per $100
Quadro P4200 Max-Q8 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 Quadro P4200 Max-Q — 8 GB VRAM.

Quadro P4200 Max-Q spec
Brand
NVIDIA
VRAM
8 GB GDDR5
Bandwidth
224.4 GB/s
FP16 Compute
0.1 TFLOPS
FP32 Compute
6.8 TFLOPS
CUDA Cores
2,304
TDP
100 W
Architecture
Pascal
AI capability
214/ 498 models @ Q4

With 8 GB VRAM and 224.4 GB/s bandwidth, this GPU handles models up to 9.63B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~26 tok/s.

Rent it — live prices
Checking what the clouds are charging…
Top models for Quadro P4200 Max-Q
214 fit · showing 20
ModelSizeVRAM Q4tok/sAvg
RecurrentGemma 9B9.63B6.4 GB1935.0
glm-4-9b9.4B6.2 GB1920.5
gemma-2-9b9.2B6.1 GB20171.8
Yi 1.5 9B9B6.0 GB2030.3
Yi Coder 9B9B6.0 GB2035.8
K2 Horizon 7B9B6.0 GB2052.4
Ministral 3 8B8.92B5.9 GB2022.6
Ministral 3 8B Reasoning8.92B5.9 GB2069.0
NVIDIA-Nemotron-Nano-9B-v28.9B5.9 GB2044.2
InternLM3 8B Instruct8.8B5.9 GB2042.8
Granite 4.2 8B8.79B5.9 GB2044.9
Gemma 1 7B8.54B5.7 GB2124.7
CodeGemma 7B8.54B5.7 GB2140.2
LFM2 8B A1B8.3B5.6 GB12024.3
Seed-Coder 8B Instruct8.25B5.5 GB2234.1
Seed-Coder 8B Reasoning8.25B5.5 GB2232.9
DeepSeek R1-0528 Qwen3 8B8.2B5.5 GB2236.3
Qwen3-8B8.2B5.5 GB2286.5
Granite 3.0 8B8.17B5.5 GB2236.4
Granite 3.1 8B8.17B5.5 GB2238.6