FitMyLLM
AMD/ GCN 1.0

AMD Radeon HD 8870 OEM

2 GB
VRAM (Budget)
154 GB/s
Memory Bandwidth
39 / 290
Models fit at Q4 (13%)
~20 tok/s
7B Q4 speed (Good)
Model coverage at Q413% of all models

Specifications

VRAM
2 GB
Bandwidth
154 GB/s
FP16 Compute
2.6 TFLOPS
TDP
175W
Memory
GDDR5
Architecture
GCN 1.0
Stream Processors
1,280
Compute Units
20
PCIe
Gen 3 x16
39
Fast models (>30 tok/s)
Real-time chat speed
39
Usable models (>10 tok/s)
Comfortable for all tasks
39
Total compatible
Fit in VRAM at Q4

Compatible Models(39)

S
GPT-2 124M0.124B
gpt21K ctxchat
1104
tok/s
18% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
1014
tok/s
18% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
999
tok/s
14% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
409
tok/s
22% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
409
tok/s
22% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
397
tok/s
24% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
380
tok/s
25% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
274
tok/s
38% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
274
tok/s
38% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
241
tok/s
30% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
228
tok/s
32% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
177
tok/s
36% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
171
tok/s
47% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
152
tok/s
50% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
137
tok/s
50% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
137
tok/s
50% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
124
tok/s
55% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
124
tok/s
55% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
114
tok/s
58% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
114
tok/s
36% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
105
tok/s
61% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
105
tok/s
59% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
105
tok/s
61% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
105
tok/s
61% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
91
tok/s
64% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
91
tok/s
67% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
91
tok/s
67% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
91
tok/s
67% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
91
tok/s
67% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
86
tok/s
69% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
81
tok/s
70% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
80
tok/s
70% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
76
tok/s
75% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
72
tok/s
68% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
68
tok/s
81% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
68
tok/s
78% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
68
tok/s
78% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
62
tok/s
84% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
60
tok/s
89% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon HD 8870 OEM.

Find Models for Radeon HD 8870 OEMCompare with other GPUs