llmrun

AMD · RDNA 3 · 48 GB VRAM tier

Best AI Models for AMD Radeon PRO W7900 (48 GB)

Runs 27–31B and 35B MoE models well; 70B barely fits and is slow (12 tok/s).

48 GB GDDR6864 GB/s123 TFLOPS FP16295 WRDNA 3 2023

What LLMs can the PRO W7900 run?

#ModelSpeed ↓llmrun ScoreQuant · VRAM
1
Qwen3.5 4BAlibabaHow to run →
Q4_K_M · 3.4 GB · 159 t/s
159 tok/sQ4_K_M · 3.4 GB
2
GPT OSS 20BOpenAI
Q4_K_M · 13.1 GB · 102 t/s
102 tok/sQ4_K_M · 13.1 GB
3
Gemma 4 26B A4B ITGoogle
Q4_K_M · 16.5 GB · 88.5 t/s
88.5 tok/sQ4_K_M · 16.5 GB
4
Qwen3.5 9BAlibaba
Q4_K_M · 6.6 GB · 81.5 t/s
81.5 tok/sQ4_K_M · 6.6 GB
5
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA
Q4_K_M · 19.3 GB · 75.8 t/s
75.8 tok/sQ4_K_M · 19.3 GB
See all 368 models on the PRO W7900 →Best quant that fits · speeds estimated on this card

About the PRO W7900

The PRO W7900 runs 27–31B and 35B MoE models well. RDNA 3 generation, released 2023.

GenerationRDNA 3released 2023

PRO W7900 strengths and weaknesses

Strengths

  • Runs 35B MoE models: Qwen3.6 35B A3B at 73.6 tok/s in 22 GB
  • Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 30.1 GB free

Weaknesses

  • 120B MoE models don't fit: GPT OSS 120B needs 70.8 GB at Q4 vs 48 GB here
  • Slow prompt reading: A 4K-token prompt on Qwen3.8 27B waits 8.4 s for the first token
  • ROCm, not CUDA: No FP8 weights; MXFP4 only through llama.cpp, not vLLM

PRO W7900 tokens per second by model size

Output speed depends on memory bandwidth (864 GB/s). Grey rows need more than 48 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    81.5tok/s
  2. 14BQwen3 14B · Q4_K_M · 11.9 GB
    54.6tok/s
  3. 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
    29.8tok/s
  4. 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
    73.6tok/s
  5. 70BLlama 3.3 70B Instruct · IQ4_XS · 46.4 GB tight · IQ4_XS
    12.4tok/s
  6. 120B MoEGPT OSS 120B · not at 4-bit
    needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 368 models on the PRO W7900

Featured only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with AMD Radeon PRO W7900 — ranked by Score, recency and Fit
ModelVRAMScoreFit
Qwen3.8 27B
Q4_K_M·29.8 t/s
17.9 GBA71, Runs well
Gemma 4 26B A4B IT
Q4_K_M·88.5 t/s
16.5 GBS89, Runs great
Muse Glimmer 30B
Q4_K_M·28.3 t/s
19.6 GBA69, Runs well
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16
Q4_K_M·75.8 t/s
19.3 GBS86, Runs great
Gemma 4 31B IT
Q4_K_M·25.4 t/s
21.7 GBA66, Runs well
GLM 4.7 Flash
Q4_K_M·66.5 t/s
19.9 GBS85, Runs great
Qwen3.6 35B A3B
Q4_K_M·73.6 t/s
22.0 GBS86, Runs great
Flint
Q4_K_M·78.5 t/s
25.0 GBS87, Runs great
JEV 27B VL
Q4_K_M·29.8 t/s
17.9 GBA71, Runs well
LFM2.5 24B A2B
Q4_K_M·91.5 t/s
15.0 GBS90, Runs great
MiniCPM V 4.7 35B A3B
Q4_K_M·78.6 t/s
22.1 GBS87, Runs great
Sage A1.5
Q4_K_M·73.6 t/s
22.0 GBS86, Runs great
MiMo V2.6 Distill Qwen 9B
Q4_K_M·83.5 t/s
6.5 GBS88, Runs great
Ling 3.0 Tiny
Q4_K_M·151.4 t/s
5.5 GBS97, Runs great
Qwen3.5 4B
Q4_K_M·159.0 t/s
3.4 GBS97, Runs great

PRO W7900 specs, power and PSU

Specs

Architecture
RDNA 3
VRAM
48 GB GDDR6
Memory bandwidth
864.0 GB/s
FP16 (dense)
122.60 TFLOPS
Stream processors
6,144
TDP
295 W
Released
2023-04-13
MSRP
$3,999

PRO W7900 FAQ

What is the largest model the PRO W7900 can run?

Qwen2.5 72B Instruct (72.7B) is the largest at 4-bit or better: at Q4_K_S it uses 46.6 GB of 48 GB, and runs at about 12.4 tok/s.

Can the PRO W7900 run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 48 GB, and it is the best model that runs well on this card.

Can the PRO W7900 run 120B MoE models?

No. GPT OSS 120B needs 70.8 GB at Q4, more than the 48 GB on this card.

How many tokens per second does the PRO W7900 give?

About 29.8 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 8.4 s on a 4K-token prompt.

What power supply does the PRO W7900 need?

Plan a 600 W PSU (2× the 295 W TDP).

Is 48 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 10 coding models that fit, runs at about 30 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Related

Best coding LLMs48 GB VRAMGPUs with 48 GB or more