FitMyLLM
AMD· TERASCALE 2

AMD FirePro V9800

VRAM
4 GB
BUDGET
BANDWIDTH
147.2
GB/S
MODELS Q4
106/449
24%
7B Q4 SPEED
~19
GOOD
▸ MODEL COVERAGE @ Q424% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~44
TOK/S
7B
3.9GB NEEDED
14B
7.9GB NEEDED
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
4 GB
BANDWIDTH
147.2 GB/s
FP16 COMPUTE
2.7 TFLOPS
TDP
250W
MEMORY
GDDR5
ARCHITECTURE
TeraScale 2
STREAM PROCESSORS
1,600
PCIE
Gen 2 x16
102
FAST MODELS · >30 TOK/S
Real-time chat speed
106
USABLE · >10 TOK/S
Comfortable for all tasks
106
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test FirePro V9800 (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· 106
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
1454
TOK/S · 14% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
969
TOK/S · 14% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
935
TOK/S · 14% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
935
TOK/S · 14% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
511
TOK/S · 16% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
485
TOK/S · 16% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
429
TOK/S · 17% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
391
TOK/S · 17% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
391
TOK/S · 17% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
391
TOK/S · 17% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
374
TOK/S · 18% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
363
TOK/S · 18% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
344
TOK/S · 18% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
262
TOK/S · 20% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
262
TOK/S · 20% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
252
TOK/S · 20% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
230
TOK/S · 21% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
230
TOK/S · 21% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
218
TOK/S · 21% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
218
TOK/S · 21% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
218
TOK/S · 21% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
211
TOK/S · 22% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
177
TOK/S · 24% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
174
TOK/S · 24% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
162
TOK/S · 25% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
150
TOK/S · 26% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
139
TOK/S · 27% VRAM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
121
TOK/S · 29% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
119
TOK/S · 29% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
109
TOK/S · 31% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
109
TOK/S · 31% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
109
TOK/S · 31% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
109
TOK/S · 31% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
101
TOK/S · 32% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
101
TOK/S · 32% VRAM
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
101
TOK/S · 32% VRAM
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
97
TOK/S · 33% VRAM
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
92
TOK/S · 34% VRAM
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
92
TOK/S · 34% VRAM
S
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
87
TOK/S · 35% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your FirePro V9800.

▸ DEVICE UNDER TEST

AMD FirePro V98004 GB VRAM.

FIREPRO V9800 SPEC
BRAND
AMD
VRAM
4 GB GDDR5
BANDWIDTH
147.2 GB/s
FP16 COMPUTE
2.7 TFLOPS
FP32 COMPUTE
2.7 TFLOPS
STREAM PROCESSORS
1,600
TDP
250 W
ARCHITECTURE
TeraScale 2
▸ AI CAPABILITY
106/ 449 models @ Q4

With 4 GB VRAM and 147.2 GB/s bandwidth, this GPU handles models up to 4.97B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~17 tok/s.

§ 01TOP MODELS FOR FIREPRO V9800
106 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
TranslateGemma 4B4.97B3.5 GB265.5
Qwen 3.5 4B4.66B3.3 GB2847.4
InternLM2 5B4.5B3.2 GB2947.6
Qwen3-VL 4B Instruct4.44B3.2 GB2926.6
MedGemma 1.5 4B4.3B3.1 GB305.5
Gemma 3 4B4.3B3.1 GB3022.8
Ministral 3 3B Reasoning4.25B3.1 GB31
Qwen 1.5 4B4B2.9 GB3312.6
Qwen3 4B4B2.9 GB3340.7
Qwen3-4B Instruct 25074B2.9 GB3337.2
Qwen3-Embedding 4B4B2.9 GB33
Granite Vision 4.1 4B4B2.9 GB33
Nemotron 3 Nano 4B3.97B2.9 GB3332.0
Ministral 3 3B3.85B2.8 GB3421.4
Phi-3.5 Mini 3.8B3.82B2.8 GB3446.6
phi-3-mini-4k 3.8B3.8B2.8 GB3430.5
Phi-4-mini 3.8B3.8B2.8 GB3449.0
Qwen2.5-VL-3B3.8B2.8 GB3429.9
Jina Embeddings v43.8B2.8 GB34
Cogito 3B3.61B2.7 GB3622.1