FitMyLLM
AMD· GCN 1.0

AMD AeroBox GPU

Running LLMs on the AeroBox GPU — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
8 GB
ENTRY-LEVEL
BANDWIDTH
68
GB/S
MODELS Q4
201/449
45%
7B Q4 SPEED
~9
USABLE
▸ MODEL COVERAGE @ Q445% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~20
TOK/S
7B
~9
TOK/S
14B
7.9GB NEEDED
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ MEASURED RIG REPORTS

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

SEE THE REPORTS
▸ SPECIFICATIONS
VRAM
8 GB
BANDWIDTH
68 GB/s
FP16 COMPUTE
3.5 TFLOPS
TDP
100W
MEMORY
DDR3
ARCHITECTURE
GCN 1.0
STREAM PROCESSORS
896
COMPUTE UNITS
14
57
FAST MODELS · >30 TOK/S
Real-time chat speed
115
USABLE · >10 TOK/S
Comfortable for all tasks
201
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test AeroBox GPU (or anything bigger) without committing. Pay by the second, cancel anytime.

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· 201
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
672
TOK/S · 7% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
448
TOK/S · 7% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
432
TOK/S · 7% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
432
TOK/S · 7% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
236
TOK/S · 8% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
224
TOK/S · 8% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
198
TOK/S · 8% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
180
TOK/S · 9% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
180
TOK/S · 9% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
180
TOK/S · 9% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
173
TOK/S · 9% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
168
TOK/S · 9% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
159
TOK/S · 9% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
121
TOK/S · 10% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
121
TOK/S · 10% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
116
TOK/S · 10% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
106
TOK/S · 10% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
106
TOK/S · 10% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
101
TOK/S · 11% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
101
TOK/S · 11% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
101
TOK/S · 11% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
97
TOK/S · 11% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
82
TOK/S · 12% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
81
TOK/S · 12% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
75
TOK/S · 12% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
69
TOK/S · 13% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
64
TOK/S · 13% VRAM
A
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
56
TOK/S · 14% VRAM
A
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
55
TOK/S · 15% VRAM
A
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
50
TOK/S · 15% VRAM
A
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
50
TOK/S · 15% VRAM
A
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
50
TOK/S · 15% VRAM
A
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
50
TOK/S · 15% VRAM
A
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
46
TOK/S · 16% VRAM
A
OPT 1.3B1.3B
OPT·2K CTX· CHAT
46
TOK/S · 16% VRAM
A
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
46
TOK/S · 16% VRAM
A
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
45
TOK/S · 16% VRAM
A
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
43
TOK/S · 17% VRAM
A
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
43
TOK/S · 17% VRAM
A
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
40
TOK/S · 70% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your AeroBox GPU.

WHAT THIS CARD IS WORTH

AeroBox GPU holds 201 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is Falcon3-10B at IQ4_XS.

TOKENS/SEC PER $100
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
what memory costs on this card
THE BIGGEST IT TAKES
Falcon3-10B10.3B · IQ4_XS7.1 GB6 tok/sEST
Bamba 9B v29.78B · Q4_K_M7.2 GB6 tok/sEST
RecurrentGemma 9B9.63B · Q4_K_M6.8 GB6 tok/sEST
glm-4-9b9.4B · Q4_K_M6.6 GB6 tok/sEST
Yi 1.5 9B9B · Q4_K_M6.5 GB6 tok/sEST
Yi Coder 9B9B · Q4_K_M6.5 GB6 tok/sEST
Ministral 3 8B8.92B · Q4_K_M6.6 GB6 tok/sEST
Ministral 3 8B Reasoning8.92B · Q4_K_M6.6 GB6 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M3 Pro (18GB)12 GB$1,5991.5 tok/s per $100
M1 Pro (16GB)11 GB$9992.9 tok/s per $100
M2 Pro (16GB)11 GB$1,2992.2 tok/s per $100
M4 (16GB)11 GB$4994.0 tok/s per $100
AeroBox GPU8 GB

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

▸ DEVICE UNDER TEST

AMD AeroBox GPU — 8 GB VRAM.

AEROBOX GPU SPEC
BRAND
AMD
VRAM
8 GB DDR3
BANDWIDTH
68 GB/s
FP16 COMPUTE
3.5 TFLOPS
FP32 COMPUTE
1.8 TFLOPS
STREAM PROCESSORS
896
TDP
100 W
ARCHITECTURE
GCN 1.0
▸ AI CAPABILITY
201/ 449 models @ Q4

With 8 GB VRAM and 68 GB/s bandwidth, this GPU handles models up to 9.63B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~8 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR AEROBOX GPU
201 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
RecurrentGemma 9B9.63B6.4 GB635.0
glm-4-9b9.4B6.2 GB620.5
gemma-2-9b9.2B6.1 GB730.2
Yi 1.5 9B9B6.0 GB730.3
Yi Coder 9B9B6.0 GB735.8
Ministral 3 8B8.92B5.9 GB725.7
Ministral 3 8B Reasoning8.92B5.9 GB7
NVIDIA-Nemotron-Nano-9B-v28.9B5.9 GB744.2
InternLM3 8B Instruct8.8B5.9 GB738.7
Gemma 1 7B8.54B5.7 GB724.7
CodeGemma 7B8.54B5.7 GB740.2
LFM2 8B A1B8.3B5.6 GB4024.3
Seed-Coder 8B Instruct8.25B5.5 GB734.1
Seed-Coder 8B Reasoning8.25B5.5 GB732.9
DeepSeek R1-0528 Qwen3 8B8.2B5.5 GB736.3
Qwen3-8B8.2B5.5 GB743.3
Granite 3.0 8B8.17B5.5 GB736.4
Granite 3.1 8B8.17B5.5 GB738.6
Command-R7B8.03B5.4 GB835.3
Aya Expanse 8B8B5.4 GB827.8