trl-internal-testing/tiny-Qwen2ForCausalLM-2.5
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5
Parameters
1.2M
Context
32K
Downloads
6M
Likes
56
Architecture
qwen2
2 layers · 2 KV heads · head 2 · hidden 8
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 2.2 GB RAM 32.0 · Disk 39.0 | 2.3 GB RAM 32.0 · Disk 65.0 | 2.4 GB RAM 32.0 · Disk 104.0 |
| FP88bit | 2.2 GB RAM 32.0 · Disk 39.0 | 2.3 GB RAM 32.0 · Disk 65.0 | 2.4 GB RAM 32.0 · Disk 104.0 |
| INT88bit | 2.2 GB RAM 32.0 · Disk 39.0 | 2.3 GB RAM 32.0 · Disk 65.0 | 2.4 GB RAM 32.0 · Disk 104.0 |
| AWQ4bit | 2.2 GB RAM 32.0 · Disk 39.0 | 2.3 GB RAM 32.0 · Disk 65.0 | 2.4 GB RAM 32.0 · Disk 104.0 |
| GPTQ4bit | 2.2 GB RAM 32.0 · Disk 39.0 | 2.3 GB RAM 32.0 · Disk 65.0 | 2.4 GB RAM 32.0 · Disk 104.0 |
| GGUF4bit | 2.2 GB RAM 32.0 · Disk 39.0 | 2.3 GB RAM 32.0 · Disk 65.0 | 2.4 GB RAM 32.0 · Disk 104.0 |
GPU Recommendations
1× RTX 3080 Ti
12 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.546
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.489
8× H200 SXM
1128 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.2197
1× RTX 4060 Ti
8 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5675
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$48.8
/mo · vast
RTX 4060 Ti
8 GB VRAM
$59.5
/mo · vast
RTX 4070S Ti
16 GB VRAM
$68.5
/mo · vast
RTX 3080
10 GB VRAM
$69.2
/mo · vast
L4
24 GB VRAM
$76.2
/mo · vast