FitMyLLM
NVIDIA/ Pascal

NVIDIA P104-100

4 GB
VRAM (Budget)
320 GB/s
Memory Bandwidth
64 / 290
Models fit at Q4 (22%)
~37 tok/s
7B Q4 speed (Fast)
Model coverage at Q422% of all models

Specifications

VRAM
4 GB
Bandwidth
320 GB/s
FP16 Compute
0.1 TFLOPS
Memory
GDDR5X
Architecture
Pascal
CUDA Cores
1,920
PCIe
Gen 1 x4
64
Fast models (>30 tok/s)
Real-time chat speed
64
Usable models (>10 tok/s)
Comfortable for all tasks
64
Total compatible
Fit in VRAM at Q4

Compatible Models(64)

S
GPT-2 124M0.124B
gpt21K ctxchat
2065
tok/s
9% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
1896
tok/s
9% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
1869
tok/s
7% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
764
tok/s
11% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
764
tok/s
11% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
742
tok/s
12% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
711
tok/s
12% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
512
tok/s
19% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
512
tok/s
19% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
451
tok/s
15% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
427
tok/s
16% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
331
tok/s
18% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
320
tok/s
23% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
284
tok/s
25% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
256
tok/s
25% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
256
tok/s
25% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
233
tok/s
28% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
233
tok/s
28% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
213
tok/s
29% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
213
tok/s
18% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
197
tok/s
30% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
197
tok/s
29% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
197
tok/s
30% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
197
tok/s
30% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
171
tok/s
32% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
171
tok/s
33% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
171
tok/s
33% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
171
tok/s
33% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
171
tok/s
33% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
160
tok/s
35% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
151
tok/s
35% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
150
tok/s
35% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
142
tok/s
38% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
135
tok/s
34% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
128
tok/s
40% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
128
tok/s
39% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
128
tok/s
39% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
116
tok/s
42% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
111
tok/s
45% VRAM
S
CodeGemma 2B2.51B
gemma8K ctxcoding
102
tok/s
46% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your P104-100.

Find Models for P104-100Compare with other GPUs