What can AMD Radeon RX 7900 XTX run for chat?

Build: RX 7900 XTX + Ryzen 9 7950X + 64GB DDR5 (Linux/ROCm)

Memory: 24 GB VRAM + 64 GB system RAM
Runner: llama.cpp (ROCm)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
174 models

Ranked by fit for chat use case + predicted speed. Click a row for VRAM breakdown.

#1Qwen 3 0.6B
0.6B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 2.6 GBHeadroom: 21.4 GBTTFT: instant
1458
tok/s
Estimated
Weights
0.30 GB
KV cache
0.30 GB
Activations
0.02 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~13 ms (instant)
Model details →
#2Llama 3.2 3B Instruct
3B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 7.1 GBHeadroom: 16.9 GBTTFT: instant
ollama run llama3.2:3b
166
tok/s
Estimated
Weights
3.40 GB
KV cache
1.50 GB
Activations
0.18 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~63 ms (instant)
Model details →
#3Qwen 3 1.7B
1.7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 3.8 GBHeadroom: 20.2 GBTTFT: instant
514
tok/s
Estimated
Weights
0.90 GB
KV cache
0.85 GB
Activations
0.05 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~35 ms (instant)
Model details →
#4TinyLlama 1.1B Chat v1.0
1.1B
llama
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.8 GBHeadroom: 21.2 GBTTFT: instant
795
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~23 ms (instant)
Model details →
#5Gemma 2 2B Instruct
2B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.2 GBHeadroom: 19.8 GBTTFT: instant
437
tok/s
Estimated
Weights
1.10 GB
KV cache
1.00 GB
Activations
0.06 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~42 ms (instant)
Model details →
#6DeepSeek V2 Lite Chat
15.7B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 18.9 GBHeadroom: 5.1 GBTTFT: instant
364
tok/s
Estimated
Weights
8.60 GB
KV cache
7.85 GB
Activations
0.44 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~50 ms (instant)
Model details →
#7Trendyol LLM 7B Chat v0.1
7B
llama
Quant: Q4_K_MContext: 4,096VRAM: 7.8 GBHeadroom: 16.2 GBTTFT: fast
125
tok/s
Estimated
Weights
3.90 GB
KV cache
1.75 GB
Activations
0.20 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Model details →
#8Kumru 2B
2.4B
mistral
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 4.8 GBHeadroom: 19.2 GBTTFT: instant
ollama run alibayram/kumru:latest
364
tok/s
Estimated
Weights
1.50 GB
KV cache
1.20 GB
Activations
0.08 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~50 ms (instant)
Model details →
#9Salamandra 7B Instruct
7B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.6 GBHeadroom: 14.4 GBTTFT: fast
125
tok/s
Estimated
Weights
3.90 GB
KV cache
3.50 GB
Activations
0.20 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Model details →
#10TinyLlama 1.1B Chat v0.3 AWQ
1.1B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.8 GBHeadroom: 21.2 GBTTFT: instant
795
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~23 ms (instant)
Model details →
#11TinyLlama 1.1B Chat v0.3 GPTQ
1.1B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 2.8 GBHeadroom: 21.2 GBTTFT: instant
795
tok/s
Estimated
Weights
0.60 GB
KV cache
0.14 GB
Activations
0.03 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~23 ms (instant)
Model details →
#12Mistral 7B Instruct v0.1
7B
mistral
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 7.8 GBHeadroom: 16.2 GBTTFT: fast
125
tok/s
Estimated
Weights
3.90 GB
KV cache
1.75 GB
Activations
0.20 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~146 ms (fast)
Model details →

Runs with tradeoffs
74 models

Tight VRAM, partial CPU offload, or context-limited.

GPT-OSS Swallow 20B RL v0.1
20B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 23.6 GBHeadroom: 0.4 GBTTFT: fast
  • • Tight VRAM fit — only 0.4 GB headroom left for context growth
44
tok/s
Estimated
Weights
11.00 GB
KV cache
10.00 GB
Activations
0.56 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~417 ms (fast)
Model details →
Sarvam M
24B
mistral
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 21.9 GBHeadroom: 2.1 GBTTFT: noticeable
  • • Tight VRAM fit — only 2.1 GB headroom left for context growth
36
tok/s
Estimated
Weights
13.20 GB
KV cache
6.00 GB
Activations
0.66 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~500 ms (noticeable)
Model details →
Gemma 4 26B MoE
26B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.1 GBHeadroom: 1.9 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.9 GB headroom left for context growth
ollama run gemma4:26b-moe
34
tok/s
Estimated
Weights
16.00 GB
KV cache
3.25 GB
Activations
0.80 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~542 ms (noticeable)
Model details →
Gemma 3 27B
27B
gemma
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 22.2 GBHeadroom: 1.8 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.8 GB headroom left for context growth
ollama run gemma3:27b
32
tok/s
Estimated
Weights
16.00 GB
KV cache
3.38 GB
Activations
0.80 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~563 ms (noticeable)
Model details →
Muse Glimmer 30B
30B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 20.6 GBHeadroom: 3.4 GBTTFT: noticeable
  • • Tight VRAM fit — only 3.4 GB headroom left for context growth
ollama run muse-glimmer
29
tok/s
Estimated
Weights
17.00 GB
KV cache
0.71 GB
Activations
0.86 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~625 ms (noticeable)
Model details →
Qwen 2.5 14B Instruct
14B
qwen
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 20.0 GBHeadroom: 4.0 GBTTFT: fast
  • • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run qwen2.5:14b
55
tok/s
Estimated
Weights
10.50 GB
KV cache
7.00 GB
Activations
0.53 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~292 ms (fast)
Model details →
Falcon 40B Instruct
40B
falcon
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 30.1 GBHeadroom: 32.3 GBTTFT: noticeable
  • • Partial CPU offload: ~20% of layers run on CPU
  • • CPU is the bottleneck — upgrading RAM bandwidth helps more than VRAM here
6
tok/s
Estimated
Weights
22.00 GB
KV cache
5.00 GB
Activations
1.10 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~834 ms (noticeable)
Model details →
Llama 3.2 11B Vision Instruct
11B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 20.6 GBHeadroom: 3.4 GBTTFT: fast
  • • Tight VRAM fit — only 3.4 GB headroom left for context growth
ollama run llama3.2-vision:11b
45
tok/s
Estimated
Weights
12.50 GB
KV cache
5.50 GB
Activations
0.63 GB
Runtime
2.00 GB
Time to first token (prefill, 512-token prompt): ~229 ms (fast)
Model details →

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 9 new comfortable, 80 new tradeoff

  • • Gemma 3 270M
  • • SmolLM2 135M Instruct
  • • SmolLM2 360M Instruct
  • • VBART Large (Turkish Summarization)
Shop this upgrade↗

Upgrade to AMD Instinct MI210

see current pricing

64 GB VRAM (vs your 24 GB) plus a bandwidth jump from ~960 GB/s to ~1638 GB/s.

Unlocks: 80 new comfortable

  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen3.6 27B
  • • Llama 3.3 70B Instruct
Shop this upgrade↗

Add a second AMD Radeon RX 7900 XTX

~$899

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 62 new comfortable

  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Qwen3.6 27B
  • • Qwen 3 32B
Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

—
Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

—
Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

—
DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

—
Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (24 GB) + 60% of system RAM (38 GB) combined.

—

How to read these numbers

Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.

Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.

Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.

Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.