FitMyLLM
AMD· RDNA3

AMD RX 7800 XT

Running LLMs on the RX 7800 XT — the long read: which models fit at which quantisation, and the settings worth changing. · Or what else $499 buys

VRAM
16 GB
MID-RANGE
BANDWIDTH
624
GB/S
MODELS Q4
262/449
58%
7B Q4 SPEED
~79
BLAZING
▸ MODEL COVERAGE @ Q458% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~185
TOK/S
7B
~79
TOK/S
14B
~40
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
16 GB
BANDWIDTH
624 GB/s
FP16 COMPUTE
75 TFLOPS
TDP
263W
MEMORY
GDDR6
ARCHITECTURE
RDNA3
STREAM PROCESSORS
3,840
COMPUTE UNITS
60
PCIE
Gen 4 x16
MSRP
$499
260
FAST MODELS · >30 TOK/S
Real-time chat speed
262
USABLE · >10 TOK/S
Comfortable for all tasks
262
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ DON’T WANT TO BUY?

Test RX 7800 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· 262
S
Falcon-H1R Tiny 90M0.09B
FALCON·256K CTX· CHAT· REASONING
6163
TOK/S · 3% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
4109
TOK/S · 4% VRAM
S
nomic-embed-text-v1.5 100M0.14B
EMBEDDING·8K CTX· CHAT
3962
TOK/S · 4% VRAM
S
GPT-2 124M0.14B
GPT2·1K CTX· CHAT
3962
TOK/S · 4% VRAM
S
SmolVLM 256M0.256B
SMOLLM·8K CTX· CHAT· VISION
2167
TOK/S · 4% VRAM
S
Gemma 3 270M0.27B
GEMMA·32K CTX· CHAT
2054
TOK/S · 4% VRAM
S
Snowflake Arctic Embed M v2.00.305B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
1819
TOK/S · 4% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
1656
TOK/S · 4% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
1656
TOK/S · 4% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
1656
TOK/S · 4% VRAM
S
LFM2 350M0.35B
LFM·125K CTX· CHAT· TOOL_USE
1585
TOK/S · 4% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
1541
TOK/S · 4% VRAM
S
GPT-2 Medium 345M0.38B
GPT2·1K CTX· CHAT
1460
TOK/S · 5% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
1109
TOK/S · 5% VRAM
S
SmolVLM 500M0.5B
SMOLLM·8K CTX· CHAT· VISION
1109
TOK/S · 5% VRAM
S
Falcon-H1 0.5B0.52B
FALCON·128K CTX· CHAT
1067
TOK/S · 5% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
977
TOK/S · 5% VRAM
S
Snowflake Arctic Embed L v2.00.568B
EMBEDDING·8K CTX· EMBEDDING· MULTILINGUAL
977
TOK/S · 5% VRAM
S
Qwen3-Embedding 0.6B0.6B
EMBEDDING·32K CTX· EMBEDDING· MULTILINGUAL
924
TOK/S · 5% VRAM
S
Falcon-H1R Tiny 0.6B0.6B
FALCON·32K CTX· CHAT· REASONING
924
TOK/S · 5% VRAM
S
Falcon Perception 0.6B0.6B
FALCON·4K CTX· VISION
924
TOK/S · 5% VRAM
S
Qwen 1.5 0.5B0.62B
QWEN·32K CTX· CHAT
895
TOK/S · 5% VRAM
S
LFM2 700M0.74B
LFM·125K CTX· CHAT· TOOL_USE
750
TOK/S · 6% VRAM
S
Qwen3 0.6B0.75B
QWEN·32K CTX· CHAT· REASONING
740
TOK/S · 6% VRAM
S
GPT-2 Large 774M0.81B
GPT2·1K CTX· CHAT
685
TOK/S · 6% VRAM
S
Qwen 3.5 0.8B0.87B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
638
TOK/S · 6% VRAM
S
InternVL3 1B0.94B
OTHER·32K CTX· CHAT· VISION
590
TOK/S · 7% VRAM
S
MiniCPM5 1B1.08B
MINICPM·128K CTX· CHAT· REASONING· MULTILINGUAL
514
TOK/S · 7% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
504
TOK/S · 7% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
462
TOK/S · 8% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
462
TOK/S · 8% VRAM
S
LFM2 1.2B1.2B
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
462
TOK/S · 8% VRAM
S
Zamba2 1.2B1.2B
OTHER·4K CTX· CHAT
462
TOK/S · 8% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
427
TOK/S · 8% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
427
TOK/S · 8% VRAM
S
MiniCPM-V 4.61.3B
OTHER·256K CTX· CHAT· VISION
427
TOK/S · 8% VRAM
S
DeepSeek Coder 1.3B1.35B
DEEPSEEK·16K CTX· CODING
411
TOK/S · 8% VRAM
S
Phi-1 1.3B1.42B
PHI·2K CTX· CODING
391
TOK/S · 8% VRAM
S
Phi-1.5 1.3B1.42B
PHI·2K CTX· CHAT· CODING
391
TOK/S · 8% VRAM
S
LFM2 8B A1B8.3BMoE
LFM·125K CTX· CHAT· TOOL_USE· MULTILINGUAL
370
TOK/S · 35% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your RX 7800 XT.

WHAT THIS CARD IS WORTH

RX 7800 XT holds 262 of the models in our catalogue and is, in practice, a IQ4_XS card — the largest it takes is ERNIE 4.5 21B A3B at IQ4_XS.

TOKENS/SEC PER $100
13.8
8B at Q4_K_M, so cards compare like for like
VRAM PER $100
3.21 GB
what memory costs on this card
THE BIGGEST IT TAKES
ERNIE 4.5 21B A3B21.95B · IQ4_XS13.9 GB146 tok/sEST
GPT-OSS 20B21B · Q4_K_S13.8 GB124 tok/sEST
Reka Flash 321B · Q4_K_S14.2 GB31 tok/sEST
Reka Flash 3.121B · Q4_K_S14.2 GB31 tok/sEST
InternLM2 20B19.8B · Q4_K_M14.3 GB31 tok/sEST
InternLM2.5 20B19.8B · Q4_K_M14.3 GB31 tok/sEST
Ling-lite 16.8B16.8B · Q5_K_M13.6 GB144 tok/sEST
DeepSeek V2 Lite 16B16B · Q5_K_M12.9 GB144 tok/sEST
AGAINST CARDS OF SIMILAR MEMORY
M1 Max (32GB)21 GB$1,4993.0 tok/s per $100
M2 Max (32GB)21 GB$1,7992.5 tok/s per $100
M2 Pro (32GB)21 GB$1,4991.9 tok/s per $100
M4 (32GB)21 GB$1,1991.7 tok/s per $100
RX 7800 XT16 GB$49913.8 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 7800 XT — 16 GB VRAM.

RX 7800 XT SPEC
BRAND
AMD
VRAM
16 GB GDDR6
BANDWIDTH
624 GB/s
FP16 COMPUTE
75 TFLOPS
FP32 COMPUTE
37 TFLOPS
STREAM PROCESSORS
3,840
TDP
263 W
ARCHITECTURE
RDNA3
MSRP
$499
▸ AI CAPABILITY
262/ 449 models @ Q4

With 16 GB VRAM and 624 GB/s bandwidth, this GPU handles models up to 19.8B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~71 tok/s.

RENT IT — LIVE PRICES
Checking what the clouds are charging…
§ 01TOP MODELS FOR RX 7800 XT
262 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
InternLM2 20B19.8B12.6 GB2845.1
InternLM2.5 20B19.8B12.6 GB2850.9
Ling-lite 16.8B16.8B10.8 GB231
DeepSeek V2 Lite 16B16B10.3 GB23138.0
StarCoder2 15B15.96B10.2 GB3526.5
DeepSeek-Coder-V2-Lite 15.7B15.7B10.1 GB23143.0
DeepSeek-VL2 Small 16B15.7B10.1 GB23143.1
StarCoder 15B15.5B10.0 GB3621.0
InternVL3 14B15.12B9.7 GB3738.1
Phi-4-reasoning-vision 15B15B9.7 GB3742.8
DeepSeek R1 Distill Qwen 14B14.8B9.5 GB3743.9
DeepCoder 14B14.8B9.5 GB3738.7
Qwen2.5-Coder-14B14.8B9.5 GB3741.3
Qwen2.5-14B14.8B9.5 GB3741.3
Qwen3 14B14.8B9.5 GB3745.7
phi-4 14B14.66B9.4 GB3833.7
Phi-4-reasoning 14B14.66B9.4 GB3833.7
Phi-4-reasoning-plus 14B14.66B9.4 GB3875.5
Ministral 3 14B14B9.0 GB4025.9
Phi-3-medium-14b14B9.0 GB4033.7