FitMyLLM
AMD· GCN 1.0

AMD FirePro D500

VRAM
3 GB
BUDGET
BANDWIDTH
243.8
GB/S
MODELS Q4
81/449
18%
7B Q4 SPEED
~31
FAST
▸ MODEL COVERAGE @ Q418% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~72
TOK/S
7B
3.9GB NEEDED
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
3 GB
BANDWIDTH
243.8 GB/s
FP16 COMPUTE
2.2 TFLOPS
TDP
274W
MEMORY
GDDR5
ARCHITECTURE
GCN 1.0
STREAM PROCESSORS
1,536
PCIE
Gen 3 x16
81
FAST MODELS · >30 TOK/S
Real-time chat speed
81
USABLE · >10 TOK/S
Comfortable for all tasks
81
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test FirePro D500 (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· 81
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
2408
TOK/S · 18% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
1605
TOK/S · 19% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
1548
TOK/S · 19% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
1548
TOK/S · 19% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
847
TOK/S · 21% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
803
TOK/S · 22% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
711
TOK/S · 22% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
647
TOK/S · 23% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
647
TOK/S · 23% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
647
TOK/S · 23% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
619
TOK/S · 23% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
602
TOK/S · 24% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
570
TOK/S · 24% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
433
TOK/S · 26% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
433
TOK/S · 26% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
417
TOK/S · 27% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
382
TOK/S · 28% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
382
TOK/S · 28% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
361
TOK/S · 29% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
361
TOK/S · 29% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
361
TOK/S · 29% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
350
TOK/S · 29% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
293
TOK/S · 31% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
289
TOK/S · 32% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
268
TOK/S · 33% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
249
TOK/S · 34% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
231
TOK/S · 35% VRAM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
201
TOK/S · 38% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
197
TOK/S · 39% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
181
TOK/S · 41% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
181
TOK/S · 41% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
181
TOK/S · 41% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
181
TOK/S · 41% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
167
TOK/S · 43% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
167
TOK/S · 43% VRAM
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
167
TOK/S · 43% VRAM
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
161
TOK/S · 44% VRAM
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
153
TOK/S · 45% VRAM
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
153
TOK/S · 45% VRAM
S
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
144
TOK/S · 47% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your FirePro D500.

WHAT THIS CARD IS WORTH

FirePro D500 holds 81 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is Falcon3-3B at Q4_K_M.

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
Falcon3-3B3.23B · Q4_K_M2.6 GB51 tok/sEST
granite-4.0-h-micro 3.2B3.2B · Q4_K_M2.6 GB51 tok/sEST
Llama-3.2-3B3.2B · Q4_K_M2.7 GB51 tok/sEST
Falcon-H1 3B3.15B · Q5_K_M2.7 GB46 tok/sEST
Qwen 2.5 3B3.1B · Q5_K_M2.6 GB47 tok/sEST
SmolLM3-3B3.1B · Q4_K_M2.5 GB52 tok/sEST
Ministral 3B3B · Q4_K_M2.6 GB53 tok/sEST
StarCoder2 3B3B · Q5_K_M2.5 GB48 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M2 (8GB)5 GB$5992.8 tok/s per $100
M3 (8GB)5 GB$5992.8 tok/s per $100
M1 (8GB)5 GB$4992.2 tok/s per $100
RTX 2060 6GB6 GB$15026.7 tok/s per $100
FirePro D5003 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 FirePro D500 — 3 GB VRAM.

FIREPRO D500 SPEC
BRAND
AMD
VRAM
3 GB GDDR5
BANDWIDTH
243.8 GB/s
FP16 COMPUTE
2.2 TFLOPS
FP32 COMPUTE
2.2 TFLOPS
STREAM PROCESSORS
1,536
TDP
274 W
ARCHITECTURE
GCN 1.0
▸ AI CAPABILITY
81/ 449 models @ Q4

With 3 GB VRAM and 243.8 GB/s bandwidth, this GPU handles models up to 3.1B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~28 tok/s.

§ 01TOP MODELS FOR FIREPRO D500
81 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Qwen 2.5 3B3.1B2.4 GB7037.2
SmolLM3-3B3.1B2.4 GB7030.5
Ministral 3B3B2.3 GB7229.6
StarCoder2 3B3B2.3 GB729.5
Granite 4.1 3B3B2.3 GB7216.6
xLAM-2 3B Function-Calling3B2.3 GB72
Jamba 2 3B3B2.3 GB72
Dolly v2 3B2.8B2.2 GB775.6
StableLM Zephyr 3B2.79B2.2 GB7814.9
Zephyr 3B2.79B2.2 GB7814.4
OPT 2.7B2.7B2.1 GB8028.0
Phi-2 2.7B2.7B2.1 GB8024.1
Zamba2 2.7B2.7B2.1 GB8048.0
Granite 3.0 2B2.63B2.1 GB8235.8
gemma-2-2b2.6B2.1 GB8322.9
LFM2 2.6B2.6B2.1 GB8316.3
Granite 3.1 2B2.53B2.0 GB8637.8
Granite 3.3 2B2.53B2.0 GB8620.5
Gemma 1 2B2.51B2.0 GB8620.2
CodeGemma 2B2.51B2.0 GB8622.9