FitMyLLM
AMD/ TeraScale 2

AMD Radeon HD 6850 X2

2 GB
VRAM (Budget)
134 GB/s
Memory Bandwidth
39 / 290
Models fit at Q4 (13%)
~17 tok/s
7B Q4 speed (Good)
Model coverage at Q413% of all models

Specifications

VRAM
2 GB
Bandwidth
134 GB/s
FP16 Compute
1.5 TFLOPS
TDP
254W
Memory
GDDR5
Architecture
TeraScale 2
Stream Processors
960
Compute Units
15
PCIe
Gen 2 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
961
tok/s
18% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
882
tok/s
18% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
869
tok/s
14% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
356
tok/s
22% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
356
tok/s
22% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
345
tok/s
24% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
331
tok/s
25% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
238
tok/s
38% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
238
tok/s
38% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
210
tok/s
30% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
199
tok/s
32% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
154
tok/s
36% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
149
tok/s
47% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
132
tok/s
50% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
119
tok/s
50% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
119
tok/s
50% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
108
tok/s
55% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
108
tok/s
55% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
99
tok/s
58% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
99
tok/s
36% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
92
tok/s
61% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
92
tok/s
59% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
92
tok/s
61% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
92
tok/s
61% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
79
tok/s
64% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
79
tok/s
67% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
79
tok/s
67% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
79
tok/s
67% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
79
tok/s
67% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
74
tok/s
69% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
70
tok/s
70% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
70
tok/s
70% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
66
tok/s
75% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
63
tok/s
68% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
60
tok/s
81% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
60
tok/s
78% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
60
tok/s
78% VRAM
A
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
54
tok/s
84% VRAM
A
Qwen3.5-2B2.3B
qwen256K ctxchat
52
tok/s
89% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon HD 6850 X2.

Find Models for Radeon HD 6850 X2Compare with other GPUs