FitMyLLM
NVIDIA/ Ampere

NVIDIA CMP 170HX 10 GB

10 GB
VRAM (Entry-level)
1560 GB/s
Memory Bandwidth
179 / 290
Models fit at Q4 (62%)
~178 tok/s
7B Q4 speed (Blazing)
Model coverage at Q462% of all models

Specifications

VRAM
10 GB
Bandwidth
1560 GB/s
FP16 Compute
50.5 TFLOPS
TDP
250W
Memory
HBM2e
Architecture
Ampere
CUDA Cores
4,480
Tensor Cores
280
PCIe
Gen 1 x4
179
Fast models (>30 tok/s)
Real-time chat speed
179
Usable models (>10 tok/s)
Comfortable for all tasks
179
Total compatible
Fit in VRAM at Q4

Compatible Models(179)

S
GPT-2 124M0.124B
gpt21K ctxchat
10065
tok/s
4% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
9244
tok/s
4% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
9109
tok/s
3% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
3725
tok/s
4% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
3725
tok/s
4% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
3617
tok/s
5% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
3467
tok/s
5% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
2496
tok/s
8% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
2496
tok/s
8% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
2197
tok/s
6% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
2080
tok/s
6% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
1612
tok/s
7% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
1560
tok/s
9% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
1387
tok/s
10% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
1248
tok/s
10% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
1248
tok/s
10% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
1135
tok/s
11% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
1135
tok/s
11% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
1040
tok/s
12% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
1040
tok/s
7% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
960
tok/s
12% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
960
tok/s
12% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
960
tok/s
12% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
960
tok/s
12% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
832
tok/s
13% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
832
tok/s
13% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
832
tok/s
13% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
832
tok/s
13% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
832
tok/s
13% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
780
tok/s
14% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
734
tok/s
14% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
730
tok/s
14% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
693
tok/s
15% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
657
tok/s
14% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
624
tok/s
44% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
624
tok/s
16% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
624
tok/s
16% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
624
tok/s
16% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
565
tok/s
17% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
543
tok/s
18% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your CMP 170HX 10 GB.

Find Models for CMP 170HX 10 GBCompare with other GPUs