FitMyLLM
AMD/ GCN 1.0

AMD Radeon HD 7970 GHz Edition

3 GB
VRAM (Budget)
288 GB/s
Memory Bandwidth
57 / 290
Models fit at Q4 (20%)
~37 tok/s
7B Q4 speed (Fast)
Model coverage at Q420% of all models

Specifications

VRAM
3 GB
Bandwidth
288 GB/s
FP16 Compute
4.3 TFLOPS
TDP
300W
Memory
GDDR5
Architecture
GCN 1.0
Stream Processors
2,048
Compute Units
32
PCIe
Gen 3 x16
57
Fast models (>30 tok/s)
Real-time chat speed
57
Usable models (>10 tok/s)
Comfortable for all tasks
57
Total compatible
Fit in VRAM at Q4

Compatible Models(57)

S
GPT-2 124M0.124B
gpt21K ctxchat
2065
tok/s
12% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
1896
tok/s
12% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
1869
tok/s
9% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
764
tok/s
15% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
764
tok/s
15% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
742
tok/s
16% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
711
tok/s
17% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
512
tok/s
26% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
512
tok/s
26% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
451
tok/s
20% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
427
tok/s
21% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
331
tok/s
24% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
320
tok/s
31% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
284
tok/s
33% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
256
tok/s
33% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
256
tok/s
33% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
233
tok/s
37% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
233
tok/s
37% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
213
tok/s
39% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
213
tok/s
24% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
197
tok/s
41% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
197
tok/s
39% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
197
tok/s
41% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
197
tok/s
41% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
171
tok/s
43% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
171
tok/s
44% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
171
tok/s
44% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
171
tok/s
44% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
171
tok/s
44% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
160
tok/s
46% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
151
tok/s
47% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
150
tok/s
47% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
142
tok/s
50% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
135
tok/s
46% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
128
tok/s
54% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
128
tok/s
52% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
128
tok/s
52% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
116
tok/s
56% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
111
tok/s
59% VRAM
S
CodeGemma 2B2.51B
gemma8K ctxcoding
102
tok/s
62% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon HD 7970 GHz Edition.

Find Models for Radeon HD 7970 GHz EditionCompare with other GPUs