FitMyLLM
▸ AMD· TERASCALE 2

AMD Radeon HD 6770 Green Edition

VRAM
2 GB
BUDGET
BANDWIDTH
21
GB/S
MODELS Q4
62/428
14%
7B Q4 SPEED
~3
SLOW
▸ MODEL COVERAGE @ Q414% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~6
TOK/S
7B
—
3.9GB NEEDED
14B
—
7.9GB NEEDED
32B
—
18.0GB NEEDED
70B
—
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
2 GB
BANDWIDTH
21 GB/s
FP16 COMPUTE
1 TFLOPS
TDP
86W
MEMORY
GDDR3
ARCHITECTURE
TeraScale 2
STREAM PROCESSORS
720
COMPUTE UNITS
11
PCIE
Gen 2 x16
23
FAST MODELS · >30 TOK/S
Real-time chat speed
55
USABLE · >10 TOK/S
Comfortable for all tasks
62
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test Radeon HD 6770 Green Edition (or anything bigger) without committing. Pay by the second, cancel anytime.

Rent on RunPod →Or Vast.ai →

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 62
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
207
TOK/S · 27% VRAM
›
S
nomic-embed-text-v1.5 100M0.1B
EMBEDDING·8K CTX· CHAT
187
TOK/S · 27% VRAM
›
S
GPT-2 124M0.124B
GPT2·1K CTX· CHAT
151
TOK/S · 28% VRAM
›
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
138
TOK/S · 29% VRAM
›
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
73
TOK/S · 32% VRAM
›
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
69
TOK/S · 33% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
61
TOK/S · 34% VRAM
›
A
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
56
TOK/S · 35% VRAM
›
A
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
56
TOK/S · 35% VRAM
›
A
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
56
TOK/S · 35% VRAM
›
A
GPT-2 Medium 345M0.345B
GPT2·1K CTX· CHAT
54
TOK/S · 35% VRAM
›
A
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
53
TOK/S · 35% VRAM
›
A
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
52
TOK/S · 35% VRAM
›
B
Falcon-H1 0.5B0.5B
FALCON·128K CTX· CHAT
37
TOK/S · 40% VRAM
›
B
Qwen 1.5 0.5B0.5B
QWEN·32K CTX· CHAT
37
TOK/S · 40% VRAM
›
B
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
37
TOK/S · 40% VRAM
›
B
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
37
TOK/S · 40% VRAM
›
B
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
33
TOK/S · 42% VRAM
›
B
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
33
TOK/S · 42% VRAM
›
B
Qwen3 0.6B0.6B
QWEN·32K CTX· CHAT· REASONING
31
TOK/S · 43% VRAM
›
B
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
31
TOK/S · 43% VRAM
›
B
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
31
TOK/S · 43% VRAM
›
B
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
31
TOK/S · 43% VRAM
›
B
LFM2 700M0.7B
LFM·125K CTX· CHAT· TOOL_USE
27
TOK/S · 46% VRAM
›
C
GPT-2 Large 774M0.774B
GPT2·1K CTX· CHAT
24
TOK/S · 48% VRAM
›
C
Qwen 3.5 0.8B0.8B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
23
TOK/S · 49% VRAM
›
C
Qwen3.5-0.8B0.9B
QWEN·256K CTX· CHAT
21
TOK/S · 52% VRAM
›
C
Falcon3-1B1B
FALCON·32K CTX· CHAT
19
TOK/S · 55% VRAM
›
C
InternLM2 1B1B
INTERNLM·32K CTX· CHAT
19
TOK/S · 55% VRAM
›
C
InternVL3 1B1B
OTHER·32K CTX· CHAT· VISION
19
TOK/S · 55% VRAM
›
C
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
17
TOK/S · 58% VRAM
›
C
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
16
TOK/S · 61% VRAM
›
C
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
16
TOK/S · 61% VRAM
›
C
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
16
TOK/S · 61% VRAM
›
C
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
16
TOK/S · 61% VRAM
›
D
DeepSeek Coder 1.3B1.3B
DEEPSEEK·16K CTX· CODING
14
TOK/S · 64% VRAM
›
D
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
14
TOK/S · 64% VRAM
›
D
OPT 1.3B1.3B
OPT·2K CTX· CHAT
14
TOK/S · 64% VRAM
›
D
Phi-1 1.3B1.3B
PHI·2K CTX· CODING
14
TOK/S · 64% VRAM
›
D
Phi-1.5 1.3B1.3B
PHI·2K CTX· CHAT· CODING
14
TOK/S · 64% VRAM
›
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon HD 6770 Green Edition.

▸Find models for Radeon HD 6770 Green EditionCompare with other GPUs
▸ DEVICE UNDER TEST

AMD Radeon HD 6770 Green Edition — 2 GB VRAM.

▸ RADEON HD 6770 GREEN EDITION SPEC
BRAND
AMD
VRAM
2 GB GDDR3
BANDWIDTH
21 GB/s
FP16 COMPUTE
1 TFLOPS
FP32 COMPUTE
1 TFLOPS
STREAM PROCESSORS
720
TDP
86 W
ARCHITECTURE
TeraScale 2
▸ AI CAPABILITY
62/ 428 models @ Q4

With 2 GB VRAM and 21 GB/s bandwidth, this GPU handles models up to 2B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~2 tok/s.

§ 01TOP MODELS FOR RADEON HD 6770 GREEN EDITION
62 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Gemma 1 2B2B1.7 GB920.2
Granite 3.0 2B2B1.7 GB935.8
Granite 3.1 2B2B1.7 GB937.8
Granite 3.3 2B2B1.7 GB920.5
Qwen 3.5 2B2B1.7 GB929.7
Qwen3-VL 2B Instruct2B1.7 GB918.4
InternVL3 2B2B1.7 GB964.9
Moondream2 1.9B1.9B1.6 GB1026.2
Qwen 1.5 1.8B1.8B1.6 GB1019.6
SmolLM2 1.7B1.71B1.5 GB1116.2
Qwen3 1.7B1.7B1.5 GB1130.1
stablelm-2-1_6b1.6B1.5 GB129.5
LFM2-VL 1.6B1.6B1.5 GB1239.7
Falcon-H1 1.5B1.5B1.4 GB1243.8
GPT-2 XL 1.5B1.5B1.4 GB125.1
Qwen2.5-Coder-1.5B1.5B1.4 GB1219.6
Qwen2 Math 1.5B1.5B1.4 GB1219.6
Qwen 2.5 1.5B1.5B1.4 GB1230.2
Yi Coder 1.5B1.5B1.4 GB1214.6
Stella en 1.5B v51.5B1.4 GB12—