FitMyLLM
AMD· GCN 1.0

AMD Radeon HD 7990

Running LLMs on the Radeon HD 7990 — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
3 GB
BUDGET
BANDWIDTH
288
GB/S
MODELS Q4
81/449
18%
7B Q4 SPEED
~37
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
~85
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
288 GB/s
FP16 COMPUTE
4.1 TFLOPS
TDP
375W
MEMORY
GDDR5
ARCHITECTURE
GCN 1.0
STREAM PROCESSORS
2,048
COMPUTE UNITS
32
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 Radeon HD 7990 (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
2844
TOK/S · 18% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
1896
TOK/S · 19% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
1829
TOK/S · 19% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
1829
TOK/S · 19% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
1000
TOK/S · 21% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
948
TOK/S · 22% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
839
TOK/S · 22% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
764
TOK/S · 23% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
764
TOK/S · 23% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
764
TOK/S · 23% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
731
TOK/S · 23% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
711
TOK/S · 24% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
674
TOK/S · 24% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
512
TOK/S · 26% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
512
TOK/S · 26% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
492
TOK/S · 27% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
451
TOK/S · 28% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
451
TOK/S · 28% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
427
TOK/S · 29% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
427
TOK/S · 29% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
427
TOK/S · 29% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
413
TOK/S · 29% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
346
TOK/S · 31% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
341
TOK/S · 32% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
316
TOK/S · 33% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
294
TOK/S · 34% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
272
TOK/S · 35% VRAM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
237
TOK/S · 38% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
233
TOK/S · 39% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
213
TOK/S · 41% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
213
TOK/S · 41% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
213
TOK/S · 41% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
213
TOK/S · 41% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
197
TOK/S · 43% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
197
TOK/S · 43% VRAM
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
197
TOK/S · 43% VRAM
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
190
TOK/S · 44% VRAM
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
180
TOK/S · 45% VRAM
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
180
TOK/S · 45% VRAM
S
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
171
TOK/S · 47% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon HD 7990.

WHAT THIS CARD IS WORTH

Radeon HD 7990 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 GB60 tok/sEST
granite-4.0-h-micro 3.2B3.2B · Q4_K_M2.6 GB60 tok/sEST
Llama-3.2-3B3.2B · Q4_K_M2.7 GB60 tok/sEST
Falcon-H1 3B3.15B · Q5_K_M2.7 GB54 tok/sEST
Qwen 2.5 3B3.1B · Q5_K_M2.6 GB55 tok/sEST
SmolLM3-3B3.1B · Q4_K_M2.5 GB62 tok/sEST
Ministral 3B3B · Q4_K_M2.6 GB63 tok/sEST
StarCoder2 3B3B · Q5_K_M2.5 GB56 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
Radeon HD 79903 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 Radeon HD 7990 — 3 GB VRAM.

RADEON HD 7990 SPEC
BRAND
AMD
VRAM
3 GB GDDR5
BANDWIDTH
288 GB/s
FP16 COMPUTE
4.1 TFLOPS
FP32 COMPUTE
4.1 TFLOPS
STREAM PROCESSORS
2,048
TDP
375 W
ARCHITECTURE
GCN 1.0
▸ AI CAPABILITY
81/ 449 models @ Q4

With 3 GB VRAM and 288 GB/s bandwidth, this GPU handles models up to 3.1B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~33 tok/s.

§ 01TOP MODELS FOR RADEON HD 7990
81 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Qwen 2.5 3B3.1B2.4 GB8337.2
SmolLM3-3B3.1B2.4 GB8330.5
Ministral 3B3B2.3 GB8529.6
StarCoder2 3B3B2.3 GB859.5
Granite 4.1 3B3B2.3 GB8516.6
xLAM-2 3B Function-Calling3B2.3 GB85
Jamba 2 3B3B2.3 GB85
Dolly v2 3B2.8B2.2 GB915.6
StableLM Zephyr 3B2.79B2.2 GB9214.9
Zephyr 3B2.79B2.2 GB9214.4
OPT 2.7B2.7B2.1 GB9528.0
Phi-2 2.7B2.7B2.1 GB9524.1
Zamba2 2.7B2.7B2.1 GB9548.0
Granite 3.0 2B2.63B2.1 GB9735.8
gemma-2-2b2.6B2.1 GB9822.9
LFM2 2.6B2.6B2.1 GB9816.3
Granite 3.1 2B2.53B2.0 GB10137.8
Granite 3.3 2B2.53B2.0 GB10120.5
Gemma 1 2B2.51B2.0 GB10220.2
CodeGemma 2B2.51B2.0 GB10222.9