FitMyLLM
AMD· RDNA3

AMD RX 7900 XT

VRAM
20 GB
MID-RANGE
BANDWIDTH
800
GB/S
MODELS Q4
276/449
61%
7B Q4 SPEED
~102
BLAZING
▸ MODEL COVERAGE @ Q461% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~237
TOK/S
7B
~102
TOK/S
14B
~51
TOK/S
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
20 GB
BANDWIDTH
800 GB/s
FP16 COMPUTE
103 TFLOPS
TDP
315W
MEMORY
GDDR6
ARCHITECTURE
RDNA3
STREAM PROCESSORS
5,376
COMPUTE UNITS
84
PCIE
Gen 4 x16
MSRP
$849
276
FAST MODELS · >30 TOK/S
Real-time chat speed
276
USABLE · >10 TOK/S
Comfortable for all tasks
276
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test RX 7900 XT (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· 276
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
7901
TOK/S · 3% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
5267
TOK/S · 3% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
5079
TOK/S · 3% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
5079
TOK/S · 3% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
2778
TOK/S · 3% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
2634
TOK/S · 3% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
2332
TOK/S · 3% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
2123
TOK/S · 3% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
2123
TOK/S · 3% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
2123
TOK/S · 3% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
2032
TOK/S · 4% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
1975
TOK/S · 4% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
1871
TOK/S · 4% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
1422
TOK/S · 4% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
1422
TOK/S · 4% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
1368
TOK/S · 4% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
1252
TOK/S · 4% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
1252
TOK/S · 4% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
1185
TOK/S · 4% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
1185
TOK/S · 4% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
1185
TOK/S · 4% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
1147
TOK/S · 4% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
961
TOK/S · 5% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
948
TOK/S · 5% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
878
TOK/S · 5% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
817
TOK/S · 5% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
757
TOK/S · 5% VRAM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
658
TOK/S · 6% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
646
TOK/S · 6% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
593
TOK/S · 6% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
593
TOK/S · 6% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
593
TOK/S · 6% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
593
TOK/S · 6% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
547
TOK/S · 6% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
547
TOK/S · 6% VRAM
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
547
TOK/S · 6% VRAM
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
527
TOK/S · 7% VRAM
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
501
TOK/S · 7% VRAM
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
501
TOK/S · 7% VRAM
S
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
474
TOK/S · 28% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your RX 7900 XT.

WHAT THIS CARD IS WORTH

RX 7900 XT holds 276 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is Qwen3.5-27B at IQ4_XS.

TOKENS/SEC PER $100
10.5
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
2.36 GB
what memory costs on this card
THE BIGGEST IT TAKES
Qwen3.5-27B27.8B · IQ4_XS17.6 GB33 tok/sEST
gemma-3-27b27.4B · IQ4_XS17.8 GB33 tok/sEST
Qwen 3.6 27B27B · IQ4_XS17.8 GB34 tok/sEST
Gemma 4 26B A4B26B · IQ4_XS17.3 GB152 tok/sEST
Aria 25B A3.9B25.3B · IQ4_XS17.7 GB155 tok/sEST
Mistral-Small-24B24B · Q4_K_M17.1 GB34 tok/sEST
Mistral-Small-3.1-24B24B · Q4_K_M17.8 GB34 tok/sEST
Magistral Small 24B24B · Q4_K_M17.1 GB34 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M3 Max (36GB)27 GB$2,4991.5 tok/s per $100
M3 Pro (36GB)27 GB$1,9991.2 tok/s per $100
M1 Max (32GB)21 GB$1,4993.0 tok/s per $100
M2 Max (32GB)21 GB$1,7992.5 tok/s per $100
RX 7900 XT20 GB$84910.5 tok/s per $100

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 RX 7900 XT — 20 GB VRAM.

RX 7900 XT SPEC
BRAND
AMD
VRAM
20 GB GDDR6
BANDWIDTH
800 GB/s
FP16 COMPUTE
103 TFLOPS
FP32 COMPUTE
52 TFLOPS
STREAM PROCESSORS
5,376
TDP
315 W
ARCHITECTURE
RDNA3
MSRP
$849
▸ AI CAPABILITY
276/ 449 models @ Q4

With 20 GB VRAM and 800 GB/s bandwidth, this GPU handles models up to 24B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~91 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR RX 7900 XT
276 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Mistral-Small-24B24B15.2 GB3025.0
Mistral-Small-3.1-24B24B15.2 GB3028.8
Magistral Small 24B24B15.2 GB3047.0
Devstral Small 2 24B24B15.2 GB3033.4
Mistral-Small-3.2-24B24B15.2 GB3044.4
LFM2 24B A2B24B15.2 GB35619.1
Devstral Small 22B23.57B14.9 GB3035.5
Codestral 22B22.2B14.1 GB3250.1
Mistral Small 22B22.2B14.1 GB3235.2
SOLAR-Pro 22B22.1B14.0 GB3244.2
ERNIE 4.5 21B A3B21.95B13.9 GB237
GPT-OSS 20B21B13.3 GB19852.9
Reka Flash 321B13.3 GB3436.2
Reka Flash 3.121B13.3 GB3433.4
InternLM2 20B19.8B12.6 GB3645.1
InternLM2.5 20B19.8B12.6 GB3650.9
Ling-lite 16.8B16.8B10.8 GB296
DeepSeek V2 Lite 16B16B10.3 GB29638.0
StarCoder2 15B15.96B10.2 GB4526.5
DeepSeek-Coder-V2-Lite 15.7B15.7B10.1 GB29643.0